Combined Code Near Final
T Rincon
4/13/2018
- 1 Recoding of BMI, age, LOS, gender, ethnicity…
- 2 Sepsis Defined
- 3 Parsing of APACHE Admit Diagnoses
- 4 Defining data variables: as.factor, as.character…
- 5 Medication Variable Decisions
- 6 Explanation of vital sign data variable decisions
- 7 ICU admit source recoded
- 8 ICU Type Decisions
- 9 Discharge locations recoded
- 10 Physician Specialties recoded
- 11 Explanation of Fuzzy Logic SIRS/OD, SIRS, SOFA, qSOFA
- 12 Inclusion/Exclusion Criteria
- 13 Preparation of data variables for Table 1
- 14 Table 1 Exclusion versus Inclusion
- 15 Checking hospital and regional level inclusion/exclusion
- 16 Descriptive
- 17 Seeding/Splitting
- 18 Baseline Mortality
- 19 Cross validation
- 20 Setting up variables to analyze interactions
- 21 Baseline Sepsis Test/Train
- 22 Cross validation
- 23 Setting up variables to analyze interactions
- 24 Table 1 Before inclusion/exclusion
- 25 Table 1 ALL After Inclusion/Exclusion
- 26 Table 1 Test Dataset
- 27 Table 1 Train Dataset
- 28 Table 2 Between Groups
- 29 Table 3 Mortality Outcome
- 30 Table 3 Sepsis Outcome
- 31 Plots for Table 3
- 32 Plots for Table 2
Sys.setenv(TZ="America/New_York")
#install.packages("tidyverse")
#install.packages("downloader")
library(dplyr); library(Hmisc); library(ggplot2); library(sjPlot); library(tidyverse); library(dplyr); library(stringr); library(downloader)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union## Loading required package: lattice## Loading required package: survival## Loading required package: Formula## Loading required package: ggplot2##
## Attaching package: 'Hmisc'## The following objects are masked from 'package:dplyr':
##
## src, summarize## The following objects are masked from 'package:base':
##
## format.pval, units## ── Attaching packages ────────────────────────────────── tidyverse 1.2.1 ──## ✔ tibble 1.4.2 ✔ purrr 0.2.4
## ✔ tidyr 0.8.0 ✔ stringr 1.3.0
## ✔ readr 1.1.1 ✔ forcats 0.3.0## ── Conflicts ───────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ✖ Hmisc::src() masks dplyr::src()
## ✖ Hmisc::summarize() masks dplyr::summarize()setwd("~/data/EICU/teresa_sepsis/")
spc <- read.csv("fuzzy_logic_score_first_day_v1_9_0_full.csv")
ssd <- read.csv("sepsis_study_data_v1_9_1_full.csv")
ap <- read.csv("apache_diagnosis_mapv2-2017-12-13.csv")
setwd("~/data/EICU/teresa_sepsis/5.0/")
ssd <- ssd %>% inner_join(spc,"patientunitstayid")
summary(ssd)## patientunitstayid exclusion_over18 exclusion_firstadmission
## Min. : 1 Min. :0.000000 Min. :0.0000
## 1st Qu.: 761960 1st Qu.:0.000000 1st Qu.:0.0000
## Median :1597616 Median :0.000000 Median :0.0000
## Mean :1647239 Mean :0.004293 Mean :0.1663
## 3rd Qu.:2628874 3rd Qu.:0.000000 3rd Qu.:0.0000
## Max. :3353271 Max. :1.000000 Max. :1.0000
##
## exclusion_yearfilter exclusion_apacheiva exclusion_vitalobservations
## Min. :0.0000 Min. :0.000 Min. :0.0000
## 1st Qu.:0.0000 1st Qu.:0.000 1st Qu.:0.0000
## Median :0.0000 Median :0.000 Median :0.0000
## Mean :0.2892 Mean :0.378 Mean :0.1026
## 3rd Qu.:1.0000 3rd Qu.:1.000 3rd Qu.:0.0000
## Max. :1.0000 Max. :1.000 Max. :1.0000
##
## exclusion_labobservations exclusion_medobservations hospitalid
## Min. :0.00000 Min. :0.0000 Min. : 1.0
## 1st Qu.:0.00000 1st Qu.:0.0000 1st Qu.:167.0
## Median :0.00000 Median :0.0000 Median :256.0
## Mean :0.02638 Mean :0.1508 Mean :257.3
## 3rd Qu.:0.00000 3rd Qu.:0.0000 3rd Qu.:365.0
## Max. :1.00000 Max. :1.0000 Max. :459.0
##
## gender age ethnicity
## : 4896 Min. : 0.00 : 47920
## Female :1309647 1st Qu.:52.00 African American: 304105
## Male :1527370 Median :65.00 Asian : 45050
## Other : 52 Mean :62.72 Caucasian :2152704
## Unknown: 556 3rd Qu.:76.00 Hispanic : 145350
## Max. :90.00 Native American : 25711
## NA's :2061 Other/Unknown : 121681
## hospital_los hospital_size hospital_type
## Min. :-6378.81 : 643295 Mode:logical
## 1st Qu.: 2.93 <100 : 141919 NA's:2842521
## Median : 5.72 100-249: 533513
## Mean : 8.94 250-500: 481826
## 3rd Qu.: 10.48 >500 :1041968
## Max. :36530.32
##
## hospital_teaching_status hospital_region
## : 554798 :632962
## f:1677818 Midwest :753120
## t: 609905 Northeast:165767
## South :714254
## West :576418
##
##
## hospital_discharge_disposition hospital_mortality
## Home :1697524 Min. :0.00
## SNF : 320193 1st Qu.:0.00
## Death : 264032 Median :0.00
## NursingHome : 147773 Mean :0.09
## Other : 136520 3rd Qu.:0.00
## OtherExternal: 121664 Max. :1.00
## (Other) : 154815 NA's :35521
## hospital_mortality_ultimate hospitaladmityear hospitaldischargeyear
## Min. :0.0 Min. :1913 Min. :1987
## 1st Qu.:0.0 1st Qu.:2010 1st Qu.:2010
## Median :0.0 Median :2012 Median :2012
## Mean :0.1 Mean :2012 Mean :2012
## 3rd Qu.:0.0 3rd Qu.:2014 3rd Qu.:2014
## Max. :1.0 Max. :2016 Max. :2016
## NA's :405081
## icu_los icu_size icu_type
## Min. : -5.3382 Mode:logical Med-Surg ICU:1527054
## 1st Qu.: 0.8278 NA's:2842521 MICU : 248339
## Median : 1.6104 CCU-CTICU : 227460
## Mean : 2.7858 Cardiac ICU : 192048
## 3rd Qu.: 3.0500 SICU : 179514
## Max. :824.2104 Neuro ICU : 164626
## (Other) : 303480
## icu_admit_source icu_disch_location
## Emergency Department:1245659 Floor :1587711
## Floor : 407519 Step-Down Unit (SDU): 291173
## Operating Room : 367328 Home : 250587
## ICU to SDU : 188944 Death : 154009
## Direct Admit : 175631 Telemetry : 152891
## Recovery Room : 109083 Other ICU : 129053
## (Other) : 348357 (Other) : 277097
## icu_mortality admitsource dischargelocation bedcount
## Min. :0.0000 Min. :-1.0 Min. :-1.0 Min. : 1.0
## 1st Qu.:0.0000 1st Qu.: 4.0 1st Qu.: 4.0 1st Qu.: 16.0
## Median :0.0000 Median : 8.0 Median : 4.0 Median : 22.0
## Mean :0.0542 Mean : 5.6 Mean : 5.1 Mean : 26.1
## 3rd Qu.:0.0000 3rd Qu.: 8.0 3rd Qu.: 7.0 3rd Qu.: 31.0
## Max. :1.0000 Max. : 8.0 Max. : 9.0 Max. :252.0
## NA's :644 NA's :405081 NA's :405081 NA's :405081
## readmit apacheiva
## Min. :0.0 Min. : -1.0
## 1st Qu.:0.0 1st Qu.: 35.0
## Median :0.0 Median : 49.0
## Mean :0.1 Mean : 52.8
## 3rd Qu.:0.0 3rd Qu.: 67.0
## Max. :1.0 Max. :230.0
## NA's :405081 NA's :1010706
## apacheadmissiondx dialysis
## : 321341 Min. :0
## Infarction, acute myocardial (MI) : 108543 1st Qu.:0
## CHF, congestive heart failure : 91037 Median :0
## Sepsis, pulmonary : 88361 Mean :0
## CVA, cerebrovascular accident/stroke : 82058 3rd Qu.:0
## CABG alone, coronary artery bypass grafting: 74389 Max. :1
## (Other) :2076792 NA's :405081
## aids hepaticfailure cirrhosis diabetes
## Min. :0 Min. :0 Min. :0 Min. :0.0
## 1st Qu.:0 1st Qu.:0 1st Qu.:0 1st Qu.:0.0
## Median :0 Median :0 Median :0 Median :0.0
## Mean :0 Mean :0 Mean :0 Mean :0.2
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0.0
## Max. :1 Max. :1 Max. :1 Max. :1.0
## NA's :405081 NA's :405081 NA's :405081 NA's :405081
## immunosuppression leukemia lymphoma metastaticcancer
## Min. :0 Min. :0 Min. :0 Min. :0
## 1st Qu.:0 1st Qu.:0 1st Qu.:0 1st Qu.:0
## Median :0 Median :0 Median :0 Median :0
## Mean :0 Mean :0 Mean :0 Mean :0
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0
## Max. :1 Max. :1 Max. :1 Max. :1
## NA's :405081 NA's :405081 NA's :405081 NA's :405081
## thrombolytics admissionheight admissionweight chartedweight
## Min. :0 Min. : 0.0 Min. : 0.0 Min. : 30.0
## 1st Qu.:0 1st Qu.:162.5 1st Qu.: 65.8 1st Qu.: 66.1
## Median :0 Median :170.0 Median : 79.4 Median : 80.0
## Mean :0 Mean :169.2 Mean : 83.3 Mean : 83.7
## 3rd Qu.:0 3rd Qu.:177.8 3rd Qu.: 95.8 3rd Qu.: 96.8
## Max. :1 Max. :720.0 Max. :993.8 Max. :300.0
## NA's :405081 NA's :142941 NA's :333094 NA's :1494918
## eyes motor verbal gcs
## Min. :-1.0 Min. :-1.0 Min. :-1.0 Min. :-3.0
## 1st Qu.: 3.0 1st Qu.: 6.0 1st Qu.: 3.0 1st Qu.:11.0
## Median : 4.0 Median : 6.0 Median : 5.0 Median :15.0
## Mean : 3.3 Mean : 5.1 Mean : 3.8 Mean :12.2
## 3rd Qu.: 4.0 3rd Qu.: 6.0 3rd Qu.: 5.0 3rd Qu.:15.0
## Max. : 4.0 Max. : 6.0 Max. : 5.0 Max. :15.0
## NA's :405081 NA's :405081 NA's :405081 NA's :405081
## unablegcs urine pao2_apache fio2_apache
## Min. :-1 Min. : -11556 Min. : -1.0 Min. : -1.0
## 1st Qu.: 0 1st Qu.: -1 1st Qu.: -1.0 1st Qu.: -1.0
## Median : 0 Median : 0 Median : -1.0 Median : -1.0
## Mean : 0 Mean : 965 Mean : 29.5 Mean : 12.8
## 3rd Qu.: 0 3rd Qu.: 1519 3rd Qu.: -1.0 3rd Qu.: -1.0
## Max. : 1 Max. :21600000 Max. :840.0 Max. :100.0
## NA's :405081 NA's :405081 NA's :405081 NA's :405081
## pao2fio2_apache temperature_apache respiratoryrate_apache
## Min. : -1.0 Min. :-1.0 Min. :-1.0
## 1st Qu.: -1.0 1st Qu.:36.0 1st Qu.:10.0
## Median : -1.0 Median :36.4 Median :25.0
## Mean : 54.9 Mean :32.6 Mean :23.3
## 3rd Qu.: -1.0 3rd Qu.:36.7 3rd Qu.:34.0
## Max. :2847.6 Max. :43.0 Max. :60.0
## NA's :405081 NA's :405081 NA's :405081
## heartrate_apache mbp_apache albumin_apache bilirubin_apache
## Min. : -1.0 Min. : -1.0 Min. :-1.0 Min. :-1.0
## 1st Qu.: 70.0 1st Qu.: 52.0 1st Qu.:-1.0 1st Qu.:-1.0
## Median :102.0 Median : 64.0 Median :-1.0 Median :-1.0
## Mean : 97.1 Mean : 82.3 Mean : 0.5 Mean :-0.2
## 3rd Qu.:119.0 3rd Qu.:120.0 3rd Qu.: 2.6 3rd Qu.: 0.5
## Max. :220.0 Max. :200.0 Max. : 8.6 Max. :72.4
## NA's :405081 NA's :405081 NA's :405081 NA's :405081
## bun_apache creatinine_apache glucose_apache hematocrit_apache
## Min. : -1.0 Min. :-1.0 Min. : -1.0 Min. :-1.0
## 1st Qu.: 6.0 1st Qu.: 0.4 1st Qu.: 85.0 1st Qu.:19.6
## Median : 15.0 Median : 0.8 Median : 118.0 Median :29.9
## Mean : 20.2 Mean : 1.0 Mean : 142.3 Mean :24.8
## 3rd Qu.: 27.0 3rd Qu.: 1.4 3rd Qu.: 191.0 3rd Qu.:35.9
## Max. :255.0 Max. :25.0 Max. :2954.0 Max. :93.0
## NA's :405081 NA's :405081 NA's :405081 NA's :405081
## sodium_apache paco2_apache ph_apache intubated_apache
## Min. : -1 Min. : -1.0 Min. :-1.0 Min. :0.0
## 1st Qu.:128 1st Qu.: -1.0 1st Qu.:-1.0 1st Qu.:0.0
## Median :136 Median : -1.0 Median :-1.0 Median :0.0
## Mean :107 Mean : 8.9 Mean : 0.9 Mean :0.1
## 3rd Qu.:140 3rd Qu.: -1.0 3rd Qu.:-1.0 3rd Qu.:0.0
## Max. :199 Max. :150.0 Max. : 8.6 Max. :1.0
## NA's :405081 NA's :405081 NA's :405081 NA's :405081
## wbc_apache oobintubday1_apache oobventday1_apache ventday1_apache
## Min. : -1.0 Min. :0.0 Min. :0.0 Min. :0.0
## 1st Qu.: -1.0 1st Qu.:0.0 1st Qu.:0.0 1st Qu.:0.0
## Median : 8.2 Median :0.0 Median :0.0 Median :0.0
## Mean : 8.7 Mean :0.2 Mean :0.3 Mean :0.2
## 3rd Qu.: 13.2 3rd Qu.:0.0 3rd Qu.:1.0 3rd Qu.:0.0
## Max. :199.7 Max. :1.0 Max. :1.0 Max. :1.0
## NA's :405081 NA's :405081 NA's :405081 NA's :405081
## physicianspeciality acutephysiologyscore apachescore
## :1010706 Min. : -1.0 Min. : -1.0
## internal medicine : 299354 1st Qu.: 25.0 1st Qu.: 35.0
## hospitalist : 259993 Median : 37.0 Median : 49.0
## cardiology : 166439 Mean : 41.4 Mean : 52.8
## pulmonary/CCM : 143113 3rd Qu.: 53.0 3rd Qu.: 67.0
## Specialty Not Specified: 142045 Max. :206.0 Max. :230.0
## (Other) : 820871 NA's :1010706 NA's :1010706
## predictedicumortality predictediculos predictedhospitalmortality
## Min. :-1.0 Min. :-1.0 Min. :-1.0
## 1st Qu.: 0.0 1st Qu.: 2.0 1st Qu.: 0.0
## Median : 0.0 Median : 3.2 Median : 0.0
## Mean : 0.0 Mean : 3.6 Mean : 0.0
## 3rd Qu.: 0.1 3rd Qu.: 5.0 3rd Qu.: 0.1
## Max. : 1.0 Max. :19.9 Max. : 1.0
## NA's :1010706 NA's :1010706 NA's :1010706
## predictedhospitallos preopmi preopcardiaccath
## Min. : -1.0 Min. :0 Min. :0
## 1st Qu.: 5.8 1st Qu.:0 1st Qu.:0
## Median : 8.8 Median :0 Median :0
## Mean : 8.9 Mean :0 Mean :0
## 3rd Qu.: 12.0 3rd Qu.:0 3rd Qu.:0
## Max. :224.9 Max. :1 Max. :1
## NA's :1010706 NA's :1010706 NA's :1010706
## ptcawithin24h graftcount mbp_min sbp_min
## Min. :0.0 Min. : 1 Min. : 1.0 Min. : 1.0
## 1st Qu.:0.0 1st Qu.: 3 1st Qu.: 48.0 1st Qu.: 50.0
## Median :0.0 Median : 3 Median : 59.0 Median : 60.0
## Mean :0.1 Mean : 3 Mean : 58.5 Mean : 60.4
## 3rd Qu.:0.0 3rd Qu.: 3 3rd Qu.: 70.0 3rd Qu.: 71.0
## Max. :1.0 Max. :10 Max. :360.0 Max. :347.0
## NA's :1010706 NA's :405081 NA's :355269 NA's :355500
## temperature_min temperature_max heartrate_max respiratoryrate_max
## Min. : 0.0 Min. : 0.1 Min. : 5.0 Min. : 1.0
## 1st Qu.: 35.0 1st Qu.: 37.3 1st Qu.: 91.0 1st Qu.: 24.0
## Median : 36.1 Median : 37.8 Median :105.0 Median : 28.0
## Mean : 40.0 Mean : 43.5 Mean :106.9 Mean : 32.1
## 3rd Qu.: 36.9 3rd Qu.: 38.5 3rd Qu.:120.0 3rd Qu.: 35.0
## Max. :137.0 Max. :224.5 Max. :300.0 Max. :63017.0
## NA's :2626885 NA's :2626885 NA's :308791 NA's :461697
## heartrate_charted_max respiratoryrate_charted_max
## Min. : 1.0 Min. : 1.0
## 1st Qu.: 85.0 1st Qu.:20.0
## Median : 98.0 Median :25.0
## Mean :100.4 Mean :26.3
## 3rd Qu.:114.0 3rd Qu.:30.0
## Max. :387.0 Max. :79.0
## NA's :702383 NA's :628438
## o2saturation_charted_min nibp_systolic_charted_min
## Min. : 0.5 Min. : 1.0
## 1st Qu.: 91.0 1st Qu.: 86.0
## Median : 94.0 Median : 99.0
## Mean : 92.1 Mean :100.6
## 3rd Qu.: 96.0 3rd Qu.:114.0
## Max. :100.0 Max. :278.0
## NA's :853531 NA's :748024
## nibp_diastolic_charted_min nibp_mean_charted_min ibp_systolic_charted_min
## Min. : 1.0 Min. : 0.1 Min. : 1.0
## 1st Qu.: 42.0 1st Qu.: 56.0 1st Qu.: 82.0
## Median : 51.0 Median : 66.0 Median : 95.0
## Mean : 51.7 Mean : 66.8 Mean : 97.4
## 3rd Qu.: 60.0 3rd Qu.: 77.0 3rd Qu.:111.0
## Max. :235.0 Max. :242.0 Max. :390.0
## NA's :746572 NA's :837390 NA's :2387420
## ibp_diastolic_charted_min ibp_mean_charted_min mbp_charted_min
## Min. : 1.0 Min. : 0.9 Min. : 0.1
## 1st Qu.: 41.0 1st Qu.: 56.0 1st Qu.: 55.0
## Median : 48.0 Median : 64.0 Median : 65.0
## Mean : 48.8 Mean : 65.4 Mean : 65.8
## 3rd Qu.: 56.0 3rd Qu.: 74.0 3rd Qu.: 76.0
## Max. :390.0 Max. :390.0 Max. :359.0
## NA's :2387543 NA's :2360225 NA's :743730
## sbp_charted_min temperature_charted_min temperature_charted_max
## Min. : 1.0 Min. :20.1 Min. :21.0
## 1st Qu.: 85.0 1st Qu.:36.1 1st Qu.:36.8
## Median : 98.0 Median :36.4 Median :37.1
## Mean : 99.1 Mean :36.3 Mean :37.3
## 3rd Qu.:113.0 3rd Qu.:36.7 3rd Qu.:37.6
## Max. :264.0 Max. :48.2 Max. :49.3
## NA's :702587 NA's :483953 NA's :483953
## gcs_charted_min bilirubin_max creatinine_max lactate_min
## Min. : 3.0 Min. : 0.0 Min. : 0.0 Min. : 0.0
## 1st Qu.:11.0 1st Qu.: 0.4 1st Qu.: 0.8 1st Qu.: 1.0
## Median :15.0 Median : 0.7 Median : 1.0 Median : 1.5
## Mean :12.5 Mean : 1.2 Mean : 1.6 Mean : 2.2
## 3rd Qu.:15.0 3rd Qu.: 1.1 3rd Qu.: 1.6 3rd Qu.: 2.3
## Max. :15.0 Max. :198.0 Max. :405.0 Max. :557.0
## NA's :1385494 NA's :1769123 NA's :457288 NA's :2348514
## lactate_max pao2_min pao2_max paco2_min
## Min. : 0.0 Min. : 0.0 Min. : 0.0 Min. :-104.0
## 1st Qu.: 1.2 1st Qu.: 67.0 1st Qu.: 86.8 1st Qu.: 31.8
## Median : 1.9 Median : 84.0 Median : 126.0 Median : 37.0
## Mean : 3.0 Mean : 102.4 Mean : 169.1 Mean : 38.9
## 3rd Qu.: 3.3 3rd Qu.: 115.0 3rd Qu.: 214.0 3rd Qu.: 43.3
## Max. :557.0 Max. :11830.0 Max. :31109.0 Max. :4560.0
## NA's :2348514 NA's :1914680 NA's :1914680 NA's :1918151
## paco2_max platelet_min inr_max wbc_min
## Min. : 0.0 Min. :-99999.0 Min. : 0.0 Min. : 0.0
## 1st Qu.: 36.0 1st Qu.: 138.0 1st Qu.: 1.1 1st Qu.: 7.3
## Median : 42.9 Median : 189.0 Median : 1.3 Median : 9.9
## Mean : 45.9 Mean : 201.2 Mean : 1.6 Mean : 11.3
## 3rd Qu.: 51.0 3rd Qu.: 248.0 3rd Qu.: 1.6 3rd Qu.: 13.5
## Max. :7572.0 Max. : 3211.0 Max. :130.0 Max. :813.9
## NA's :1918151 NA's :555601 NA's :1836686 NA's :551423
## wbc_max ptt_max bands_max ph_min
## Min. : 0.0 Min. :-180.0 Min. : 0.0 Min. : -7.3
## 1st Qu.: 7.9 1st Qu.: 28.9 1st Qu.: 3.0 1st Qu.: 7.3
## Median : 10.8 Median : 34.0 Median : 8.0 Median : 7.3
## Mean : 12.6 Mean : 45.3 Mean : 12.9 Mean : 7.6
## 3rd Qu.: 14.9 3rd Qu.: 46.8 3rd Qu.: 18.0 3rd Qu.: 7.4
## Max. :346000.0 Max. :2935.0 Max. :6424.0 Max. :70566.0
## NA's :551423 NA's :2093556 NA's :2610683 NA's :1926604
## basedeficit_min basedeficit_max ast_max alt_max
## Min. :-30.0 Min. :-30.0 Min. : -68.0 Min. : -645.0
## 1st Qu.: 2.4 1st Qu.: 2.4 1st Qu.: 20.0 1st Qu.: 18.0
## Median : 4.8 Median : 4.8 Median : 32.0 Median : 29.0
## Mean : 6.1 Mean : 6.1 Mean : 166.9 Mean : 105.6
## 3rd Qu.: 8.0 3rd Qu.: 8.0 3rd Qu.: 67.0 3rd Qu.: 51.0
## Max. :405.0 Max. :405.0 Max. :787878.0 Max. :474747.0
## NA's :2698012 NA's :2698012 NA's :1745541 NA's :1760955
## alp_max penicilin penicilin_anti_staph
## Min. : -154.0 Min. :0 Min. :0
## 1st Qu.: 59.0 1st Qu.:0 1st Qu.:0
## Median : 79.0 Median :0 Median :0
## Mean : 107.4 Mean :0 Mean :0
## 3rd Qu.: 111.0 3rd Qu.:0 3rd Qu.:0
## Max. :868488.0 Max. :1 Max. :1
## NA's :1770314 NA's :472327 NA's :472327
## penicilin_anti_pseudo augmentin_unasyn cephalosporin_1st_gen
## Min. :0.0 Min. :0 Min. :0
## 1st Qu.:0.0 1st Qu.:0 1st Qu.:0
## Median :0.0 Median :0 Median :0
## Mean :0.1 Mean :0 Mean :0
## 3rd Qu.:0.0 3rd Qu.:0 3rd Qu.:0
## Max. :1.0 Max. :1 Max. :1
## NA's :472327 NA's :472327 NA's :472327
## cephalosporin_2nd_gen cephalosporin_3rd_gen cephalosporin_4th_5th_gen
## Min. :0 Min. :0.0 Min. :0
## 1st Qu.:0 1st Qu.:0.0 1st Qu.:0
## Median :0 Median :0.0 Median :0
## Mean :0 Mean :0.1 Mean :0
## 3rd Qu.:0 3rd Qu.:0.0 3rd Qu.:0
## Max. :1 Max. :1.0 Max. :1
## NA's :472327 NA's :472327 NA's :472327
## carbapenems monobactam fq vancomycin
## Min. :0 Min. :0 Min. :0.0 Min. :0.0
## 1st Qu.:0 1st Qu.:0 1st Qu.:0.0 1st Qu.:0.0
## Median :0 Median :0 Median :0.0 Median :0.0
## Mean :0 Mean :0 Mean :0.1 Mean :0.2
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0.0 3rd Qu.:0.0
## Max. :1 Max. :1 Max. :1.0 Max. :1.0
## NA's :472327 NA's :472327 NA's :472327 NA's :472327
## amg polymixins linezolid dapto
## Min. :0 Min. :0 Min. :0 Min. :0
## 1st Qu.:0 1st Qu.:0 1st Qu.:0 1st Qu.:0
## Median :0 Median :0 Median :0 Median :0
## Mean :0 Mean :0 Mean :0 Mean :0
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0
## Max. :1 Max. :1 Max. :1 Max. :1
## NA's :472327 NA's :472327 NA's :472327 NA's :472327
## clinda doxycyclin macrolides sulfa
## Min. :0 Min. :0 Min. :0 Min. :0
## 1st Qu.:0 1st Qu.:0 1st Qu.:0 1st Qu.:0
## Median :0 Median :0 Median :0 Median :0
## Mean :0 Mean :0 Mean :0 Mean :0
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0
## Max. :1 Max. :1 Max. :1 Max. :1
## NA's :472327 NA's :472327 NA's :472327 NA's :472327
## metronidazole nitrofurantoin tigecycline ceftriaxone
## Min. :0 Min. :0 Min. :0 Min. :0
## 1st Qu.:0 1st Qu.:0 1st Qu.:0 1st Qu.:0
## Median :0 Median :0 Median :0 Median :0
## Mean :0 Mean :0 Mean :0 Mean :0
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0
## Max. :1 Max. :1 Max. :1 Max. :0
## NA's :472327 NA's :472327 NA's :472327 NA's :472327
## cefotaxime ampicillin_sulbactam levofloxacin moxifloxacin
## Min. :0 Min. :0 Min. :0 Min. :0
## 1st Qu.:0 1st Qu.:0 1st Qu.:0 1st Qu.:0
## Median :0 Median :0 Median :0 Median :0
## Mean :0 Mean :0 Mean :0 Mean :0
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0
## Max. :0 Max. :0 Max. :1 Max. :1
## NA's :472327 NA's :472327 NA's :472327 NA's :472327
## piperacillin_tazobactam cefepim meropenem
## Min. :0 Min. :0 Min. :0
## 1st Qu.:0 1st Qu.:0 1st Qu.:0
## Median :0 Median :0 Median :0
## Mean :0 Mean :0 Mean :0
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0
## Max. :0 Max. :0 Max. :0
## NA's :472327 NA's :472327 NA's :472327
## imipenem doripenem gentamicin tobramycin
## Min. :0 Min. :0 Min. :0 Min. :0
## 1st Qu.:0 1st Qu.:0 1st Qu.:0 1st Qu.:0
## Median :0 Median :0 Median :0 Median :0
## Mean :0 Mean :0 Mean :0 Mean :0
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0
## Max. :0 Max. :0 Max. :1 Max. :1
## NA's :472327 NA's :472327 NA's :472327 NA's :472327
## amikacin dopamine_infusion epinephrine_infusion
## Min. :0 Min. :0.0 Min. :0
## 1st Qu.:0 1st Qu.:0.0 1st Qu.:0
## Median :0 Median :0.0 Median :0
## Mean :0 Mean :0.1 Mean :0
## 3rd Qu.:0 3rd Qu.:0.0 3rd Qu.:0
## Max. :0 Max. :1.0 Max. :1
## NA's :472327 NA's :2005993 NA's :2005993
## norepinephrine_infusion phenylephrine_infusion vasopressin_infusion
## Min. :0.0 Min. :0.0 Min. :0
## 1st Qu.:0.0 1st Qu.:0.0 1st Qu.:0
## Median :0.0 Median :0.0 Median :0
## Mean :0.2 Mean :0.1 Mean :0
## 3rd Qu.:0.0 3rd Qu.:0.0 3rd Qu.:0
## Max. :1.0 Max. :1.0 Max. :1
## NA's :2005993 NA's :2005993 NA's :2005993
## milrinone_infusion heparin_infusion dopamine_medication
## Min. :0 Min. :0.0 Min. :0.0
## 1st Qu.:0 1st Qu.:0.0 1st Qu.:0.0
## Median :0 Median :0.0 Median :0.0
## Mean :0 Mean :0.1 Mean :0.1
## 3rd Qu.:0 3rd Qu.:0.0 3rd Qu.:0.0
## Max. :1 Max. :1.0 Max. :1.0
## NA's :2005993 NA's :2005993 NA's :472327
## epinephrine_medication norepinephrine_medication phenylephrine_medication
## Min. :0 Min. :0.0 Min. :0.0
## 1st Qu.:0 1st Qu.:0.0 1st Qu.:0.0
## Median :0 Median :0.0 Median :0.0
## Mean :0 Mean :0.1 Mean :0.1
## 3rd Qu.:0 3rd Qu.:0.0 3rd Qu.:0.0
## Max. :1 Max. :1.0 Max. :1.0
## NA's :472327 NA's :472327 NA's :472327
## vasopressin_medication milrinone_medication heparin_medication
## Min. :0 Min. :0 Min. :0.0
## 1st Qu.:0 1st Qu.:0 1st Qu.:0.0
## Median :0 Median :0 Median :0.0
## Mean :0 Mean :0 Mean :0.2
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:0.0
## Max. :1 Max. :1 Max. :1.0
## NA's :472327 NA's :472327 NA's :472327
## sepsis sepsis_priority infection infection_priority
## Min. :0.0 Min. :0.0 Min. :0.0 Min. :0.0
## 1st Qu.:0.0 1st Qu.:0.0 1st Qu.:0.0 1st Qu.:0.0
## Median :0.0 Median :0.0 Median :0.0 Median :0.0
## Mean :0.1 Mean :0.2 Mean :0.3 Mean :0.5
## 3rd Qu.:0.0 3rd Qu.:0.0 3rd Qu.:1.0 3rd Qu.:1.0
## Max. :1.0 Max. :3.0 Max. :1.0 Max. :3.0
## NA's :451180 NA's :451180 NA's :451180 NA's :451180
## aidshiv aidshiv_priority organfailure organfailure_priority
## Min. :0 Min. :0 Min. :0.0 Min. :0.0
## 1st Qu.:0 1st Qu.:0 1st Qu.:0.0 1st Qu.:0.0
## Median :0 Median :0 Median :0.0 Median :0.0
## Mean :0 Mean :0 Mean :0.4 Mean :0.7
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:1.0 3rd Qu.:1.0
## Max. :1 Max. :3 Max. :1.0 Max. :3.0
## NA's :451180 NA's :451180 NA's :451180 NA's :451180
## altered_mental_status altered_mental_status_priority infection_apache
## Min. :0.0 Min. :0.0 Min. :0.0
## 1st Qu.:0.0 1st Qu.:0.0 1st Qu.:0.0
## Median :0.0 Median :0.0 Median :0.0
## Mean :0.1 Mean :0.2 Mean :0.2
## 3rd Qu.:0.0 3rd Qu.:0.0 3rd Qu.:0.0
## Max. :1.0 Max. :3.0 Max. :1.0
## NA's :451180 NA's :451180 NA's :405081
## organfailure_apache prompt_inflam prompt_severe_sepsis
## Min. :0.0 Min. :0.0 Min. :0.0
## 1st Qu.:0.0 1st Qu.:0.0 1st Qu.:0.0
## Median :0.0 Median :0.0 Median :0.0
## Mean :0.1 Mean :0.2 Mean :0.1
## 3rd Qu.:0.0 3rd Qu.:0.0 3rd Qu.:0.0
## Max. :1.0 Max. :1.0 Max. :1.0
## NA's :405081 NA's :2043713 NA's :2043713
## prompt_sepsis prompt_inflam_with_org_dys prompt_clinical_respone_req
## Min. :0 Min. :0 Min. :0
## 1st Qu.:0 1st Qu.:0 1st Qu.:1
## Median :0 Median :0 Median :1
## Mean :0 Mean :0 Mean :1
## 3rd Qu.:0 3rd Qu.:0 3rd Qu.:1
## Max. :1 Max. :1 Max. :1
## NA's :2043713 NA's :2043713 NA's :2043713
## sofa_respiration sofa_coagulation sofa_liver sofa_cardiovascular
## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0
## 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0
## Median :0.0000 Median :0.0000 Median :0.0000 Median :1
## Mean :0.2906 Mean :0.3582 Mean :0.1393 Mean :1
## 3rd Qu.:0.0000 3rd Qu.:0.0000 3rd Qu.:0.0000 3rd Qu.:1
## Max. :4.0000 Max. :4.0000 Max. :4.0000 Max. :3
##
## sofa_cns sofa_renal sofa_renal_baseline sofa_liver_baseline
## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
## 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000
## Median :0.0000 Median :0.0000 Median :0.0000 Median :0.0000
## Mean :0.6754 Mean :0.7193 Mean :0.1244 Mean :0.0704
## 3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:0.0000 3rd Qu.:0.0000
## Max. :4.0000 Max. :4.0000 Max. :4.0000 Max. :4.0000
##
## sofa_respiration_baseline cardiovascular_baseline soi_alpha
## Min. :0.000 Min. :0.0000 Min. :2.5
## 1st Qu.:0.000 1st Qu.:0.0000 1st Qu.:2.6
## Median :0.000 Median :0.0000 Median :2.8
## Mean :0.403 Mean :0.1942 Mean :3.0
## 3rd Qu.:0.000 3rd Qu.:0.0000 3rd Qu.:3.1
## Max. :2.000 Max. :1.0000 Max. :8.0
## NA's :1172186
## soi_minutes od_alpha od_minutes both_soi_alpha
## Min. : -60.0 Min. :1.0 Min. : -60.0 Min. :2.5
## 1st Qu.: 0.0 1st Qu.:1.0 1st Qu.: -60.0 1st Qu.:2.6
## Median : 45.0 Median :1.0 Median : 20.0 Median :2.9
## Mean : 196.7 Mean :1.2 Mean : 161.3 Mean :3.1
## 3rd Qu.: 265.0 3rd Qu.:1.0 3rd Qu.: 225.0 3rd Qu.:3.3
## Max. :1440.0 Max. :7.0 Max. :1440.0 Max. :9.0
## NA's :1172186 NA's :735024 NA's :735024 NA's :1523008
## both_od_alpha both_minutes soi_alteredmentalstatus
## Min. :1.0 Min. : -60.0 Min. :0
## 1st Qu.:1.0 1st Qu.: 5.0 1st Qu.:0
## Median :1.0 Median : 80.0 Median :0
## Mean :1.4 Mean : 243.1 Mean :0
## 3rd Qu.:2.0 3rd Qu.: 375.0 3rd Qu.:0
## Max. :7.0 Max. :1440.0 Max. :1
## NA's :1523008 NA's :1523008 NA's :1172186
## soi_glucose soi_heartrate soi_inr soi_respiratoryrate
## Min. :0.0 Min. :0.0 Min. :0.0 Min. :0.0
## 1st Qu.:0.0 1st Qu.:0.3 1st Qu.:0.0 1st Qu.:0.4
## Median :0.9 Median :0.9 Median :0.0 Median :0.8
## Mean :0.6 Mean :0.7 Mean :0.2 Mean :0.6
## 3rd Qu.:1.0 3rd Qu.:1.0 3rd Qu.:0.0 3rd Qu.:1.0
## Max. :1.0 Max. :1.0 Max. :1.0 Max. :1.0
## NA's :1172186 NA's :1172186 NA's :1172186 NA's :1172186
## soi_temperature soi_bands soi_wbc soi_lactate
## Min. :0.0 Min. :0.0 Min. :0.0 Min. :0.0
## 1st Qu.:0.0 1st Qu.:0.0 1st Qu.:0.0 1st Qu.:0.0
## Median :0.0 Median :0.0 Median :0.6 Median :0.0
## Mean :0.2 Mean :0.1 Mean :0.5 Mean :0.1
## 3rd Qu.:0.2 3rd Qu.:0.0 3rd Qu.:1.0 3rd Qu.:0.0
## Max. :1.0 Max. :1.0 Max. :1.0 Max. :1.0
## NA's :1172186 NA's :1172186 NA's :1172186 NA's :1172186
## od_liver od_cardiovascular od_respiratory od_kidney
## Min. :0.0 Min. :0.0 Min. :0.0 Min. :0.0
## 1st Qu.:0.0 1st Qu.:0.0 1st Qu.:0.0 1st Qu.:0.0
## Median :0.0 Median :1.0 Median :0.0 Median :0.0
## Mean :0.1 Mean :0.6 Mean :0.2 Mean :0.1
## 3rd Qu.:0.0 3rd Qu.:1.0 3rd Qu.:0.0 3rd Qu.:0.0
## Max. :1.0 Max. :1.0 Max. :1.0 Max. :1.0
## NA's :735024 NA's :735024 NA's :735024 NA's :735024
## od_lactate od_metabolic od_hematologic
## Min. :0.0 Min. :0.0 Min. :0
## 1st Qu.:0.0 1st Qu.:0.0 1st Qu.:0
## Median :0.0 Median :0.0 Median :0
## Mean :0.1 Mean :0.1 Mean :0
## 3rd Qu.:0.0 3rd Qu.:0.0 3rd Qu.:0
## Max. :1.0 Max. :1.0 Max. :1
## NA's :735024 NA's :735024 NA's :735024
## both_soi_alteredmentalstatus both_soi_glucose both_soi_heartrate
## Min. :0 Min. :0.0 Min. :0.0
## 1st Qu.:0 1st Qu.:0.0 1st Qu.:0.3
## Median :0 Median :0.8 Median :0.9
## Mean :0 Mean :0.6 Mean :0.7
## 3rd Qu.:0 3rd Qu.:1.0 3rd Qu.:1.0
## Max. :1 Max. :1.0 Max. :1.0
## NA's :1523008 NA's :1523008 NA's :1523008
## both_soi_inr both_soi_respiratoryrate both_soi_temperature
## Min. :0.0 Min. :0.0 Min. :0.0
## 1st Qu.:0.0 1st Qu.:0.4 1st Qu.:0.0
## Median :0.0 Median :0.8 Median :0.0
## Mean :0.2 Mean :0.6 Mean :0.2
## 3rd Qu.:0.2 3rd Qu.:1.0 3rd Qu.:0.2
## Max. :1.0 Max. :1.0 Max. :1.0
## NA's :1523008 NA's :1523008 NA's :1523008
## both_soi_bands both_soi_wbc both_soi_lactate both_od_liver
## Min. :0.0 Min. :0.0 Min. :0.0 Min. :0.0
## 1st Qu.:0.0 1st Qu.:0.0 1st Qu.:0.0 1st Qu.:0.0
## Median :0.0 Median :0.7 Median :0.0 Median :0.0
## Mean :0.1 Mean :0.6 Mean :0.2 Mean :0.2
## 3rd Qu.:0.0 3rd Qu.:1.0 3rd Qu.:0.0 3rd Qu.:0.0
## Max. :1.0 Max. :1.0 Max. :1.0 Max. :1.0
## NA's :1523008 NA's :1523008 NA's :1523008 NA's :1523008
## both_od_cardiovascular both_od_respiratory both_od_kidney
## Min. :0.0 Min. :0.0 Min. :0.0
## 1st Qu.:0.0 1st Qu.:0.0 1st Qu.:0.0
## Median :1.0 Median :0.0 Median :0.0
## Mean :0.5 Mean :0.2 Mean :0.1
## 3rd Qu.:1.0 3rd Qu.:0.0 3rd Qu.:0.0
## Max. :1.0 Max. :1.0 Max. :1.0
## NA's :1523008 NA's :1523008 NA's :1523008
## both_od_lactate both_od_metabolic both_od_hematologic
## Min. :0.0 Min. :0.0 Min. :0
## 1st Qu.:0.0 1st Qu.:0.0 1st Qu.:0
## Median :0.0 Median :0.0 Median :0
## Mean :0.2 Mean :0.2 Mean :0
## 3rd Qu.:0.0 3rd Qu.:0.0 3rd Qu.:0
## Max. :1.0 Max. :1.0 Max. :1
## NA's :1523008 NA's :1523008 NA's :1523008colnames(ssd)## [1] "patientunitstayid" "exclusion_over18"
## [3] "exclusion_firstadmission" "exclusion_yearfilter"
## [5] "exclusion_apacheiva" "exclusion_vitalobservations"
## [7] "exclusion_labobservations" "exclusion_medobservations"
## [9] "hospitalid" "gender"
## [11] "age" "ethnicity"
## [13] "hospital_los" "hospital_size"
## [15] "hospital_type" "hospital_teaching_status"
## [17] "hospital_region" "hospital_discharge_disposition"
## [19] "hospital_mortality" "hospital_mortality_ultimate"
## [21] "hospitaladmityear" "hospitaldischargeyear"
## [23] "icu_los" "icu_size"
## [25] "icu_type" "icu_admit_source"
## [27] "icu_disch_location" "icu_mortality"
## [29] "admitsource" "dischargelocation"
## [31] "bedcount" "readmit"
## [33] "apacheiva" "apacheadmissiondx"
## [35] "dialysis" "aids"
## [37] "hepaticfailure" "cirrhosis"
## [39] "diabetes" "immunosuppression"
## [41] "leukemia" "lymphoma"
## [43] "metastaticcancer" "thrombolytics"
## [45] "admissionheight" "admissionweight"
## [47] "chartedweight" "eyes"
## [49] "motor" "verbal"
## [51] "gcs" "unablegcs"
## [53] "urine" "pao2_apache"
## [55] "fio2_apache" "pao2fio2_apache"
## [57] "temperature_apache" "respiratoryrate_apache"
## [59] "heartrate_apache" "mbp_apache"
## [61] "albumin_apache" "bilirubin_apache"
## [63] "bun_apache" "creatinine_apache"
## [65] "glucose_apache" "hematocrit_apache"
## [67] "sodium_apache" "paco2_apache"
## [69] "ph_apache" "intubated_apache"
## [71] "wbc_apache" "oobintubday1_apache"
## [73] "oobventday1_apache" "ventday1_apache"
## [75] "physicianspeciality" "acutephysiologyscore"
## [77] "apachescore" "predictedicumortality"
## [79] "predictediculos" "predictedhospitalmortality"
## [81] "predictedhospitallos" "preopmi"
## [83] "preopcardiaccath" "ptcawithin24h"
## [85] "graftcount" "mbp_min"
## [87] "sbp_min" "temperature_min"
## [89] "temperature_max" "heartrate_max"
## [91] "respiratoryrate_max" "heartrate_charted_max"
## [93] "respiratoryrate_charted_max" "o2saturation_charted_min"
## [95] "nibp_systolic_charted_min" "nibp_diastolic_charted_min"
## [97] "nibp_mean_charted_min" "ibp_systolic_charted_min"
## [99] "ibp_diastolic_charted_min" "ibp_mean_charted_min"
## [101] "mbp_charted_min" "sbp_charted_min"
## [103] "temperature_charted_min" "temperature_charted_max"
## [105] "gcs_charted_min" "bilirubin_max"
## [107] "creatinine_max" "lactate_min"
## [109] "lactate_max" "pao2_min"
## [111] "pao2_max" "paco2_min"
## [113] "paco2_max" "platelet_min"
## [115] "inr_max" "wbc_min"
## [117] "wbc_max" "ptt_max"
## [119] "bands_max" "ph_min"
## [121] "basedeficit_min" "basedeficit_max"
## [123] "ast_max" "alt_max"
## [125] "alp_max" "penicilin"
## [127] "penicilin_anti_staph" "penicilin_anti_pseudo"
## [129] "augmentin_unasyn" "cephalosporin_1st_gen"
## [131] "cephalosporin_2nd_gen" "cephalosporin_3rd_gen"
## [133] "cephalosporin_4th_5th_gen" "carbapenems"
## [135] "monobactam" "fq"
## [137] "vancomycin" "amg"
## [139] "polymixins" "linezolid"
## [141] "dapto" "clinda"
## [143] "doxycyclin" "macrolides"
## [145] "sulfa" "metronidazole"
## [147] "nitrofurantoin" "tigecycline"
## [149] "ceftriaxone" "cefotaxime"
## [151] "ampicillin_sulbactam" "levofloxacin"
## [153] "moxifloxacin" "piperacillin_tazobactam"
## [155] "cefepim" "meropenem"
## [157] "imipenem" "doripenem"
## [159] "gentamicin" "tobramycin"
## [161] "amikacin" "dopamine_infusion"
## [163] "epinephrine_infusion" "norepinephrine_infusion"
## [165] "phenylephrine_infusion" "vasopressin_infusion"
## [167] "milrinone_infusion" "heparin_infusion"
## [169] "dopamine_medication" "epinephrine_medication"
## [171] "norepinephrine_medication" "phenylephrine_medication"
## [173] "vasopressin_medication" "milrinone_medication"
## [175] "heparin_medication" "sepsis"
## [177] "sepsis_priority" "infection"
## [179] "infection_priority" "aidshiv"
## [181] "aidshiv_priority" "organfailure"
## [183] "organfailure_priority" "altered_mental_status"
## [185] "altered_mental_status_priority" "infection_apache"
## [187] "organfailure_apache" "prompt_inflam"
## [189] "prompt_severe_sepsis" "prompt_sepsis"
## [191] "prompt_inflam_with_org_dys" "prompt_clinical_respone_req"
## [193] "sofa_respiration" "sofa_coagulation"
## [195] "sofa_liver" "sofa_cardiovascular"
## [197] "sofa_cns" "sofa_renal"
## [199] "sofa_renal_baseline" "sofa_liver_baseline"
## [201] "sofa_respiration_baseline" "cardiovascular_baseline"
## [203] "soi_alpha" "soi_minutes"
## [205] "od_alpha" "od_minutes"
## [207] "both_soi_alpha" "both_od_alpha"
## [209] "both_minutes" "soi_alteredmentalstatus"
## [211] "soi_glucose" "soi_heartrate"
## [213] "soi_inr" "soi_respiratoryrate"
## [215] "soi_temperature" "soi_bands"
## [217] "soi_wbc" "soi_lactate"
## [219] "od_liver" "od_cardiovascular"
## [221] "od_respiratory" "od_kidney"
## [223] "od_lactate" "od_metabolic"
## [225] "od_hematologic" "both_soi_alteredmentalstatus"
## [227] "both_soi_glucose" "both_soi_heartrate"
## [229] "both_soi_inr" "both_soi_respiratoryrate"
## [231] "both_soi_temperature" "both_soi_bands"
## [233] "both_soi_wbc" "both_soi_lactate"
## [235] "both_od_liver" "both_od_cardiovascular"
## [237] "both_od_respiratory" "both_od_kidney"
## [239] "both_od_lactate" "both_od_metabolic"
## [241] "both_od_hematologic"nrow(ssd)## [1] 28425211 Recoding of BMI, age, LOS, gender, ethnicity…
ssd <- ssd %>% mutate(patientweight = ifelse (is.na (chartedweight), (admissionweight),chartedweight))
ssd$BMI <- ssd$patientweight/((ssd$admissionheight/100)^2)
ssd$BMI_Ranges <- cut(ssd$BMI, c(0, 18.5, 25, 35, 200))
ssd <- ssd %>% mutate (BMI_Ranges=as.factor(if_else(is.na(BMI_Ranges),"Other/Unknown", as.character(BMI_Ranges))))
summary(ssd$BMI_Ranges, useNA = "ifany")## (0,18.5] (18.5,25] (25,35] (35,200] Other/Unknown
## 128213 753213 1191774 453265 316056table(ssd$BMI_Ranges,useNA = "ifany")##
## (0,18.5] (18.5,25] (25,35] (35,200] Other/Unknown
## 128213 753213 1191774 453265 316056ssd$age_Ranges <- cut(ssd$age, c(0, 25, 35, 45, 55, 65, 75, 85, 100))
table(ssd$age_Ranges,useNA = "ifany")##
## (0,25] (25,35] (35,45] (45,55] (55,65] (65,75] (75,85] (85,100]
## 105109 141150 215032 421325 585296 621393 526359 224233
## <NA>
## 2624ssd%>%filter(is.na(age_Ranges))%>%select(age_Ranges, age)## age_Ranges age
## 1 <NA> NA
## 2 <NA> 0
## 3 <NA> NA
## 4 <NA> NA
## 5 <NA> NA
## 6 <NA> NA
## 7 <NA> NA
## 8 <NA> NA
## 9 <NA> NA
## 10 <NA> NA
## 11 <NA> NA
## 12 <NA> NA
## 13 <NA> NA
## 14 <NA> NA
## 15 <NA> NA
## 16 <NA> NA
## 17 <NA> NA
## 18 <NA> NA
## 19 <NA> 0
## 20 <NA> NA
## 21 <NA> NA
## 22 <NA> NA
## 23 <NA> NA
## 24 <NA> NA
## 25 <NA> NA
## 26 <NA> NA
## 27 <NA> NA
## 28 <NA> NA
## 29 <NA> NA
## 30 <NA> NA
## 31 <NA> NA
## 32 <NA> NA
## 33 <NA> NA
## 34 <NA> 0
## 35 <NA> 0
## 36 <NA> NA
## 37 <NA> NA
## 38 <NA> NA
## 39 <NA> 0
## 40 <NA> NA
## 41 <NA> NA
## 42 <NA> NA
## 43 <NA> NA
## 44 <NA> NA
## 45 <NA> NA
## 46 <NA> NA
## 47 <NA> NA
## 48 <NA> NA
## 49 <NA> NA
## 50 <NA> NA
## 51 <NA> NA
## 52 <NA> NA
## 53 <NA> NA
## 54 <NA> NA
## 55 <NA> NA
## 56 <NA> NA
## 57 <NA> NA
## 58 <NA> NA
## 59 <NA> NA
## 60 <NA> NA
## 61 <NA> NA
## 62 <NA> NA
## 63 <NA> NA
## 64 <NA> NA
## 65 <NA> NA
## 66 <NA> NA
## 67 <NA> NA
## 68 <NA> NA
## 69 <NA> NA
## 70 <NA> NA
## 71 <NA> NA
## 72 <NA> NA
## 73 <NA> 0
## 74 <NA> 0
## 75 <NA> NA
## 76 <NA> NA
## 77 <NA> NA
## 78 <NA> NA
## 79 <NA> NA
## 80 <NA> NA
## 81 <NA> NA
## 82 <NA> NA
## 83 <NA> NA
## 84 <NA> NA
## 85 <NA> NA
## 86 <NA> NA
## 87 <NA> NA
## 88 <NA> NA
## 89 <NA> NA
## 90 <NA> NA
## 91 <NA> NA
## 92 <NA> NA
## 93 <NA> NA
## 94 <NA> NA
## 95 <NA> NA
## 96 <NA> NA
## 97 <NA> NA
## 98 <NA> NA
## 99 <NA> NA
## 100 <NA> NA
## 101 <NA> NA
## 102 <NA> NA
## 103 <NA> NA
## 104 <NA> NA
## 105 <NA> NA
## 106 <NA> NA
## 107 <NA> NA
## 108 <NA> NA
## 109 <NA> NA
## 110 <NA> NA
## 111 <NA> NA
## 112 <NA> 0
## 113 <NA> 0
## 114 <NA> NA
## 115 <NA> NA
## 116 <NA> NA
## 117 <NA> NA
## 118 <NA> NA
## 119 <NA> NA
## 120 <NA> NA
## 121 <NA> NA
## 122 <NA> NA
## 123 <NA> NA
## 124 <NA> NA
## 125 <NA> NA
## 126 <NA> 0
## 127 <NA> 0
## 128 <NA> NA
## 129 <NA> NA
## 130 <NA> NA
## 131 <NA> NA
## 132 <NA> NA
## 133 <NA> NA
## 134 <NA> NA
## 135 <NA> NA
## 136 <NA> NA
## 137 <NA> NA
## 138 <NA> NA
## 139 <NA> NA
## 140 <NA> NA
## 141 <NA> NA
## 142 <NA> NA
## 143 <NA> NA
## 144 <NA> NA
## 145 <NA> NA
## 146 <NA> NA
## 147 <NA> NA
## 148 <NA> NA
## 149 <NA> NA
## 150 <NA> NA
## 151 <NA> NA
## 152 <NA> 0
## 153 <NA> NA
## 154 <NA> NA
## 155 <NA> NA
## 156 <NA> NA
## 157 <NA> NA
## 158 <NA> NA
## 159 <NA> NA
## 160 <NA> 0
## 161 <NA> NA
## 162 <NA> NA
## 163 <NA> 0
## 164 <NA> NA
## 165 <NA> NA
## 166 <NA> NA
## 167 <NA> NA
## 168 <NA> NA
## 169 <NA> NA
## 170 <NA> NA
## 171 <NA> NA
## 172 <NA> NA
## 173 <NA> NA
## 174 <NA> NA
## 175 <NA> NA
## 176 <NA> NA
## 177 <NA> 0
## 178 <NA> NA
## 179 <NA> NA
## 180 <NA> NA
## 181 <NA> NA
## 182 <NA> NA
## 183 <NA> NA
## 184 <NA> NA
## 185 <NA> NA
## 186 <NA> NA
## 187 <NA> NA
## 188 <NA> NA
## 189 <NA> NA
## 190 <NA> 0
## 191 <NA> NA
## 192 <NA> NA
## 193 <NA> NA
## 194 <NA> NA
## 195 <NA> NA
## 196 <NA> NA
## 197 <NA> NA
## 198 <NA> NA
## 199 <NA> NA
## 200 <NA> NA
## 201 <NA> NA
## 202 <NA> NA
## 203 <NA> NA
## 204 <NA> NA
## 205 <NA> NA
## 206 <NA> NA
## 207 <NA> NA
## 208 <NA> NA
## 209 <NA> NA
## 210 <NA> NA
## 211 <NA> NA
## 212 <NA> NA
## 213 <NA> NA
## 214 <NA> NA
## 215 <NA> NA
## 216 <NA> NA
## 217 <NA> NA
## 218 <NA> NA
## 219 <NA> NA
## 220 <NA> NA
## 221 <NA> NA
## 222 <NA> 0
## 223 <NA> NA
## 224 <NA> NA
## 225 <NA> NA
## 226 <NA> NA
## 227 <NA> NA
## 228 <NA> NA
## 229 <NA> NA
## 230 <NA> NA
## 231 <NA> NA
## 232 <NA> NA
## 233 <NA> NA
## 234 <NA> NA
## 235 <NA> NA
## 236 <NA> NA
## 237 <NA> NA
## 238 <NA> NA
## 239 <NA> NA
## 240 <NA> NA
## 241 <NA> NA
## 242 <NA> NA
## 243 <NA> NA
## 244 <NA> NA
## 245 <NA> NA
## 246 <NA> NA
## 247 <NA> NA
## 248 <NA> NA
## 249 <NA> NA
## 250 <NA> NA
## 251 <NA> NA
## 252 <NA> NA
## 253 <NA> NA
## 254 <NA> NA
## 255 <NA> NA
## 256 <NA> NA
## 257 <NA> NA
## 258 <NA> NA
## 259 <NA> NA
## 260 <NA> NA
## 261 <NA> NA
## 262 <NA> NA
## 263 <NA> NA
## 264 <NA> NA
## 265 <NA> NA
## 266 <NA> NA
## 267 <NA> NA
## 268 <NA> NA
## 269 <NA> NA
## 270 <NA> NA
## 271 <NA> NA
## 272 <NA> NA
## 273 <NA> NA
## 274 <NA> NA
## 275 <NA> NA
## 276 <NA> NA
## 277 <NA> NA
## 278 <NA> NA
## 279 <NA> NA
## 280 <NA> NA
## 281 <NA> NA
## 282 <NA> NA
## 283 <NA> NA
## 284 <NA> NA
## 285 <NA> NA
## 286 <NA> NA
## 287 <NA> NA
## 288 <NA> NA
## 289 <NA> NA
## 290 <NA> NA
## 291 <NA> NA
## 292 <NA> NA
## 293 <NA> NA
## 294 <NA> NA
## 295 <NA> NA
## 296 <NA> NA
## 297 <NA> NA
## 298 <NA> NA
## 299 <NA> NA
## 300 <NA> NA
## 301 <NA> NA
## 302 <NA> NA
## 303 <NA> NA
## 304 <NA> NA
## 305 <NA> NA
## 306 <NA> NA
## 307 <NA> NA
## 308 <NA> NA
## 309 <NA> NA
## 310 <NA> NA
## 311 <NA> NA
## 312 <NA> NA
## 313 <NA> NA
## 314 <NA> NA
## 315 <NA> NA
## 316 <NA> NA
## 317 <NA> NA
## 318 <NA> NA
## 319 <NA> NA
## 320 <NA> NA
## 321 <NA> NA
## 322 <NA> NA
## 323 <NA> NA
## 324 <NA> NA
## 325 <NA> NA
## 326 <NA> NA
## 327 <NA> NA
## 328 <NA> NA
## 329 <NA> NA
## 330 <NA> NA
## 331 <NA> NA
## 332 <NA> NA
## 333 <NA> NA
## 334 <NA> NA
## 335 <NA> NA
## 336 <NA> 0
## 337 <NA> NA
## 338 <NA> NA
## 339 <NA> NA
## 340 <NA> NA
## 341 <NA> NA
## 342 <NA> NA
## 343 <NA> NA
## 344 <NA> NA
## 345 <NA> NA
## 346 <NA> NA
## 347 <NA> NA
## 348 <NA> NA
## 349 <NA> NA
## 350 <NA> NA
## 351 <NA> NA
## 352 <NA> NA
## 353 <NA> NA
## 354 <NA> 0
## 355 <NA> NA
## 356 <NA> NA
## 357 <NA> NA
## 358 <NA> 0
## 359 <NA> NA
## 360 <NA> NA
## 361 <NA> NA
## 362 <NA> NA
## 363 <NA> NA
## 364 <NA> NA
## 365 <NA> NA
## 366 <NA> NA
## 367 <NA> NA
## 368 <NA> NA
## 369 <NA> 0
## 370 <NA> NA
## 371 <NA> NA
## 372 <NA> NA
## 373 <NA> NA
## 374 <NA> NA
## 375 <NA> NA
## 376 <NA> NA
## 377 <NA> NA
## 378 <NA> NA
## 379 <NA> NA
## 380 <NA> NA
## 381 <NA> NA
## 382 <NA> NA
## 383 <NA> NA
## 384 <NA> NA
## 385 <NA> NA
## 386 <NA> NA
## 387 <NA> NA
## 388 <NA> NA
## 389 <NA> NA
## 390 <NA> NA
## 391 <NA> NA
## 392 <NA> NA
## 393 <NA> 0
## 394 <NA> 0
## 395 <NA> NA
## 396 <NA> NA
## 397 <NA> NA
## 398 <NA> NA
## 399 <NA> NA
## 400 <NA> NA
## 401 <NA> NA
## 402 <NA> NA
## 403 <NA> NA
## 404 <NA> NA
## 405 <NA> NA
## 406 <NA> NA
## 407 <NA> NA
## 408 <NA> NA
## 409 <NA> NA
## 410 <NA> NA
## 411 <NA> NA
## 412 <NA> NA
## 413 <NA> NA
## 414 <NA> NA
## 415 <NA> NA
## 416 <NA> NA
## 417 <NA> NA
## 418 <NA> NA
## 419 <NA> NA
## 420 <NA> NA
## 421 <NA> NA
## 422 <NA> NA
## 423 <NA> NA
## 424 <NA> NA
## 425 <NA> NA
## 426 <NA> NA
## 427 <NA> NA
## 428 <NA> NA
## 429 <NA> NA
## 430 <NA> NA
## 431 <NA> NA
## 432 <NA> NA
## 433 <NA> 0
## 434 <NA> NA
## 435 <NA> 0
## 436 <NA> NA
## 437 <NA> NA
## 438 <NA> NA
## 439 <NA> NA
## 440 <NA> NA
## 441 <NA> NA
## 442 <NA> NA
## 443 <NA> NA
## 444 <NA> NA
## 445 <NA> NA
## 446 <NA> NA
## 447 <NA> NA
## 448 <NA> NA
## 449 <NA> NA
## 450 <NA> 0
## 451 <NA> 0
## 452 <NA> 0
## 453 <NA> NA
## 454 <NA> NA
## 455 <NA> NA
## 456 <NA> NA
## 457 <NA> NA
## 458 <NA> 0
## 459 <NA> NA
## 460 <NA> NA
## 461 <NA> NA
## 462 <NA> NA
## 463 <NA> NA
## 464 <NA> NA
## 465 <NA> NA
## 466 <NA> NA
## 467 <NA> NA
## 468 <NA> NA
## 469 <NA> NA
## 470 <NA> NA
## 471 <NA> NA
## 472 <NA> NA
## 473 <NA> NA
## 474 <NA> NA
## 475 <NA> NA
## 476 <NA> NA
## 477 <NA> NA
## 478 <NA> NA
## 479 <NA> NA
## 480 <NA> NA
## 481 <NA> NA
## 482 <NA> NA
## 483 <NA> NA
## 484 <NA> NA
## 485 <NA> NA
## 486 <NA> NA
## 487 <NA> NA
## 488 <NA> NA
## 489 <NA> NA
## 490 <NA> NA
## 491 <NA> NA
## 492 <NA> NA
## 493 <NA> NA
## 494 <NA> NA
## 495 <NA> NA
## 496 <NA> NA
## 497 <NA> NA
## 498 <NA> NA
## 499 <NA> NA
## 500 <NA> NA
## 501 <NA> NA
## 502 <NA> NA
## 503 <NA> NA
## 504 <NA> NA
## 505 <NA> NA
## 506 <NA> NA
## 507 <NA> NA
## 508 <NA> NA
## 509 <NA> NA
## 510 <NA> NA
## 511 <NA> NA
## 512 <NA> NA
## 513 <NA> NA
## 514 <NA> NA
## 515 <NA> NA
## 516 <NA> NA
## 517 <NA> NA
## 518 <NA> 0
## 519 <NA> NA
## 520 <NA> NA
## 521 <NA> NA
## 522 <NA> NA
## 523 <NA> NA
## 524 <NA> NA
## 525 <NA> NA
## 526 <NA> NA
## 527 <NA> NA
## 528 <NA> NA
## 529 <NA> NA
## 530 <NA> NA
## 531 <NA> NA
## 532 <NA> NA
## 533 <NA> NA
## 534 <NA> NA
## 535 <NA> NA
## 536 <NA> NA
## 537 <NA> NA
## 538 <NA> NA
## 539 <NA> NA
## 540 <NA> NA
## 541 <NA> NA
## 542 <NA> NA
## 543 <NA> NA
## 544 <NA> NA
## 545 <NA> NA
## 546 <NA> NA
## 547 <NA> NA
## 548 <NA> NA
## 549 <NA> 0
## 550 <NA> 0
## 551 <NA> NA
## 552 <NA> NA
## 553 <NA> NA
## 554 <NA> NA
## 555 <NA> 0
## 556 <NA> 0
## 557 <NA> 0
## 558 <NA> NA
## 559 <NA> NA
## 560 <NA> NA
## 561 <NA> 0
## 562 <NA> NA
## 563 <NA> NA
## 564 <NA> 0
## 565 <NA> NA
## 566 <NA> NA
## 567 <NA> NA
## 568 <NA> NA
## 569 <NA> 0
## 570 <NA> 0
## 571 <NA> NA
## 572 <NA> NA
## 573 <NA> 0
## 574 <NA> NA
## 575 <NA> NA
## 576 <NA> 0
## 577 <NA> NA
## 578 <NA> NA
## 579 <NA> NA
## 580 <NA> NA
## 581 <NA> NA
## 582 <NA> NA
## 583 <NA> NA
## 584 <NA> NA
## 585 <NA> NA
## 586 <NA> NA
## 587 <NA> 0
## 588 <NA> NA
## 589 <NA> NA
## 590 <NA> 0
## 591 <NA> NA
## 592 <NA> NA
## 593 <NA> 0
## 594 <NA> NA
## 595 <NA> NA
## 596 <NA> NA
## 597 <NA> NA
## 598 <NA> NA
## 599 <NA> NA
## 600 <NA> NA
## 601 <NA> NA
## 602 <NA> NA
## 603 <NA> NA
## 604 <NA> NA
## 605 <NA> NA
## 606 <NA> NA
## 607 <NA> NA
## 608 <NA> NA
## 609 <NA> NA
## 610 <NA> NA
## 611 <NA> NA
## 612 <NA> NA
## 613 <NA> NA
## 614 <NA> NA
## 615 <NA> NA
## 616 <NA> NA
## 617 <NA> NA
## 618 <NA> NA
## 619 <NA> NA
## 620 <NA> NA
## 621 <NA> NA
## 622 <NA> NA
## 623 <NA> NA
## 624 <NA> NA
## 625 <NA> NA
## 626 <NA> NA
## 627 <NA> NA
## 628 <NA> NA
## 629 <NA> NA
## 630 <NA> NA
## 631 <NA> NA
## 632 <NA> NA
## 633 <NA> NA
## 634 <NA> NA
## 635 <NA> NA
## 636 <NA> NA
## 637 <NA> NA
## 638 <NA> NA
## 639 <NA> NA
## 640 <NA> NA
## 641 <NA> NA
## 642 <NA> NA
## 643 <NA> NA
## 644 <NA> NA
## 645 <NA> NA
## 646 <NA> NA
## 647 <NA> NA
## 648 <NA> NA
## 649 <NA> NA
## 650 <NA> NA
## 651 <NA> NA
## 652 <NA> NA
## 653 <NA> NA
## 654 <NA> NA
## 655 <NA> NA
## 656 <NA> NA
## 657 <NA> NA
## 658 <NA> NA
## 659 <NA> NA
## 660 <NA> NA
## 661 <NA> NA
## 662 <NA> NA
## 663 <NA> NA
## 664 <NA> NA
## 665 <NA> NA
## 666 <NA> NA
## 667 <NA> NA
## 668 <NA> NA
## 669 <NA> NA
## 670 <NA> NA
## 671 <NA> NA
## 672 <NA> NA
## 673 <NA> NA
## 674 <NA> NA
## 675 <NA> NA
## 676 <NA> NA
## 677 <NA> NA
## 678 <NA> NA
## 679 <NA> NA
## 680 <NA> NA
## 681 <NA> NA
## 682 <NA> NA
## 683 <NA> NA
## 684 <NA> NA
## 685 <NA> NA
## 686 <NA> NA
## 687 <NA> NA
## 688 <NA> NA
## 689 <NA> NA
## 690 <NA> NA
## 691 <NA> NA
## 692 <NA> NA
## 693 <NA> NA
## 694 <NA> NA
## 695 <NA> NA
## 696 <NA> NA
## 697 <NA> NA
## 698 <NA> NA
## 699 <NA> NA
## 700 <NA> NA
## 701 <NA> NA
## 702 <NA> NA
## 703 <NA> NA
## 704 <NA> NA
## 705 <NA> NA
## 706 <NA> NA
## 707 <NA> NA
## 708 <NA> NA
## 709 <NA> NA
## 710 <NA> NA
## 711 <NA> NA
## 712 <NA> NA
## 713 <NA> NA
## 714 <NA> NA
## 715 <NA> NA
## 716 <NA> NA
## 717 <NA> NA
## 718 <NA> NA
## 719 <NA> NA
## 720 <NA> NA
## 721 <NA> NA
## 722 <NA> NA
## 723 <NA> NA
## 724 <NA> NA
## 725 <NA> NA
## 726 <NA> NA
## 727 <NA> NA
## 728 <NA> NA
## 729 <NA> NA
## 730 <NA> NA
## 731 <NA> NA
## 732 <NA> NA
## 733 <NA> NA
## 734 <NA> NA
## 735 <NA> NA
## 736 <NA> NA
## 737 <NA> NA
## 738 <NA> NA
## 739 <NA> NA
## 740 <NA> NA
## 741 <NA> NA
## 742 <NA> NA
## 743 <NA> NA
## 744 <NA> NA
## 745 <NA> NA
## 746 <NA> NA
## 747 <NA> NA
## 748 <NA> NA
## 749 <NA> NA
## 750 <NA> NA
## 751 <NA> NA
## 752 <NA> NA
## 753 <NA> NA
## 754 <NA> NA
## 755 <NA> NA
## 756 <NA> NA
## 757 <NA> NA
## 758 <NA> NA
## 759 <NA> NA
## 760 <NA> NA
## 761 <NA> NA
## 762 <NA> NA
## 763 <NA> NA
## 764 <NA> NA
## 765 <NA> NA
## 766 <NA> NA
## 767 <NA> NA
## 768 <NA> NA
## 769 <NA> NA
## 770 <NA> NA
## 771 <NA> NA
## 772 <NA> NA
## 773 <NA> NA
## 774 <NA> NA
## 775 <NA> NA
## 776 <NA> NA
## 777 <NA> NA
## 778 <NA> NA
## 779 <NA> NA
## 780 <NA> NA
## 781 <NA> NA
## 782 <NA> NA
## 783 <NA> NA
## 784 <NA> NA
## 785 <NA> NA
## 786 <NA> NA
## 787 <NA> NA
## 788 <NA> NA
## 789 <NA> NA
## 790 <NA> NA
## 791 <NA> NA
## 792 <NA> NA
## 793 <NA> NA
## 794 <NA> NA
## 795 <NA> NA
## 796 <NA> NA
## 797 <NA> NA
## 798 <NA> NA
## 799 <NA> NA
## 800 <NA> NA
## 801 <NA> NA
## 802 <NA> NA
## 803 <NA> NA
## 804 <NA> NA
## 805 <NA> NA
## 806 <NA> NA
## 807 <NA> NA
## 808 <NA> NA
## 809 <NA> NA
## 810 <NA> NA
## 811 <NA> NA
## 812 <NA> NA
## 813 <NA> NA
## 814 <NA> NA
## 815 <NA> NA
## 816 <NA> NA
## 817 <NA> NA
## 818 <NA> NA
## 819 <NA> NA
## 820 <NA> NA
## 821 <NA> NA
## 822 <NA> NA
## 823 <NA> NA
## 824 <NA> NA
## 825 <NA> NA
## 826 <NA> NA
## 827 <NA> NA
## 828 <NA> NA
## 829 <NA> NA
## 830 <NA> NA
## 831 <NA> NA
## 832 <NA> NA
## 833 <NA> NA
## 834 <NA> NA
## 835 <NA> NA
## 836 <NA> NA
## 837 <NA> NA
## 838 <NA> NA
## 839 <NA> NA
## 840 <NA> NA
## 841 <NA> NA
## 842 <NA> NA
## 843 <NA> NA
## 844 <NA> NA
## 845 <NA> NA
## 846 <NA> NA
## 847 <NA> NA
## 848 <NA> NA
## 849 <NA> NA
## 850 <NA> NA
## 851 <NA> NA
## 852 <NA> NA
## 853 <NA> NA
## 854 <NA> NA
## 855 <NA> NA
## 856 <NA> NA
## 857 <NA> NA
## 858 <NA> NA
## 859 <NA> NA
## 860 <NA> NA
## 861 <NA> NA
## 862 <NA> NA
## 863 <NA> NA
## 864 <NA> NA
## 865 <NA> NA
## 866 <NA> NA
## 867 <NA> NA
## 868 <NA> NA
## 869 <NA> NA
## 870 <NA> NA
## 871 <NA> NA
## 872 <NA> NA
## 873 <NA> NA
## 874 <NA> NA
## 875 <NA> NA
## 876 <NA> NA
## 877 <NA> NA
## 878 <NA> NA
## 879 <NA> NA
## 880 <NA> NA
## 881 <NA> NA
## 882 <NA> NA
## 883 <NA> NA
## 884 <NA> NA
## 885 <NA> NA
## 886 <NA> NA
## 887 <NA> NA
## 888 <NA> NA
## 889 <NA> NA
## 890 <NA> NA
## 891 <NA> NA
## 892 <NA> NA
## 893 <NA> NA
## 894 <NA> NA
## 895 <NA> NA
## 896 <NA> NA
## 897 <NA> NA
## 898 <NA> NA
## 899 <NA> NA
## 900 <NA> NA
## 901 <NA> NA
## 902 <NA> NA
## 903 <NA> NA
## 904 <NA> NA
## 905 <NA> NA
## 906 <NA> NA
## 907 <NA> NA
## 908 <NA> NA
## 909 <NA> NA
## 910 <NA> NA
## 911 <NA> NA
## 912 <NA> NA
## 913 <NA> NA
## 914 <NA> NA
## 915 <NA> NA
## 916 <NA> NA
## 917 <NA> NA
## 918 <NA> NA
## 919 <NA> NA
## 920 <NA> NA
## 921 <NA> NA
## 922 <NA> NA
## 923 <NA> NA
## 924 <NA> NA
## 925 <NA> NA
## 926 <NA> NA
## 927 <NA> NA
## 928 <NA> NA
## 929 <NA> NA
## 930 <NA> NA
## 931 <NA> NA
## 932 <NA> NA
## 933 <NA> NA
## 934 <NA> NA
## 935 <NA> NA
## 936 <NA> NA
## 937 <NA> NA
## 938 <NA> NA
## 939 <NA> NA
## 940 <NA> NA
## 941 <NA> NA
## 942 <NA> NA
## 943 <NA> NA
## 944 <NA> NA
## 945 <NA> NA
## 946 <NA> NA
## 947 <NA> NA
## 948 <NA> NA
## 949 <NA> NA
## 950 <NA> NA
## 951 <NA> NA
## 952 <NA> NA
## 953 <NA> NA
## 954 <NA> NA
## 955 <NA> NA
## 956 <NA> NA
## 957 <NA> NA
## 958 <NA> NA
## 959 <NA> NA
## 960 <NA> NA
## 961 <NA> NA
## 962 <NA> NA
## 963 <NA> NA
## 964 <NA> NA
## 965 <NA> NA
## 966 <NA> NA
## 967 <NA> NA
## 968 <NA> NA
## 969 <NA> NA
## 970 <NA> NA
## 971 <NA> NA
## 972 <NA> NA
## 973 <NA> NA
## 974 <NA> NA
## 975 <NA> NA
## 976 <NA> NA
## 977 <NA> NA
## 978 <NA> NA
## 979 <NA> NA
## 980 <NA> NA
## 981 <NA> NA
## 982 <NA> NA
## 983 <NA> NA
## 984 <NA> NA
## 985 <NA> NA
## 986 <NA> NA
## 987 <NA> NA
## 988 <NA> NA
## 989 <NA> NA
## 990 <NA> NA
## 991 <NA> NA
## 992 <NA> NA
## 993 <NA> NA
## 994 <NA> NA
## 995 <NA> NA
## 996 <NA> NA
## 997 <NA> NA
## 998 <NA> NA
## 999 <NA> NA
## 1000 <NA> NA
## 1001 <NA> NA
## 1002 <NA> NA
## 1003 <NA> NA
## 1004 <NA> NA
## 1005 <NA> NA
## 1006 <NA> NA
## 1007 <NA> NA
## 1008 <NA> NA
## 1009 <NA> NA
## 1010 <NA> NA
## 1011 <NA> NA
## 1012 <NA> NA
## 1013 <NA> NA
## 1014 <NA> NA
## 1015 <NA> NA
## 1016 <NA> NA
## 1017 <NA> NA
## 1018 <NA> NA
## 1019 <NA> NA
## 1020 <NA> NA
## 1021 <NA> NA
## 1022 <NA> NA
## 1023 <NA> NA
## 1024 <NA> NA
## 1025 <NA> NA
## 1026 <NA> NA
## 1027 <NA> NA
## 1028 <NA> NA
## 1029 <NA> NA
## 1030 <NA> NA
## 1031 <NA> NA
## 1032 <NA> NA
## 1033 <NA> NA
## 1034 <NA> NA
## 1035 <NA> NA
## 1036 <NA> NA
## 1037 <NA> NA
## 1038 <NA> NA
## 1039 <NA> NA
## 1040 <NA> NA
## 1041 <NA> NA
## 1042 <NA> NA
## 1043 <NA> NA
## 1044 <NA> NA
## 1045 <NA> NA
## 1046 <NA> NA
## 1047 <NA> NA
## 1048 <NA> NA
## 1049 <NA> NA
## 1050 <NA> NA
## 1051 <NA> NA
## 1052 <NA> NA
## 1053 <NA> NA
## 1054 <NA> NA
## 1055 <NA> NA
## 1056 <NA> NA
## 1057 <NA> NA
## 1058 <NA> NA
## 1059 <NA> NA
## 1060 <NA> NA
## 1061 <NA> NA
## 1062 <NA> NA
## 1063 <NA> NA
## 1064 <NA> NA
## 1065 <NA> NA
## 1066 <NA> NA
## 1067 <NA> NA
## 1068 <NA> NA
## 1069 <NA> NA
## 1070 <NA> NA
## 1071 <NA> NA
## 1072 <NA> NA
## 1073 <NA> NA
## 1074 <NA> NA
## 1075 <NA> NA
## 1076 <NA> NA
## 1077 <NA> NA
## 1078 <NA> NA
## 1079 <NA> NA
## 1080 <NA> NA
## 1081 <NA> NA
## 1082 <NA> NA
## 1083 <NA> NA
## 1084 <NA> NA
## 1085 <NA> NA
## 1086 <NA> NA
## 1087 <NA> NA
## 1088 <NA> NA
## 1089 <NA> NA
## 1090 <NA> NA
## 1091 <NA> NA
## 1092 <NA> NA
## 1093 <NA> NA
## 1094 <NA> NA
## 1095 <NA> NA
## 1096 <NA> NA
## 1097 <NA> NA
## 1098 <NA> NA
## 1099 <NA> NA
## 1100 <NA> NA
## 1101 <NA> NA
## 1102 <NA> NA
## 1103 <NA> NA
## 1104 <NA> NA
## 1105 <NA> NA
## 1106 <NA> NA
## 1107 <NA> NA
## 1108 <NA> NA
## 1109 <NA> NA
## 1110 <NA> NA
## 1111 <NA> NA
## 1112 <NA> NA
## 1113 <NA> NA
## 1114 <NA> NA
## 1115 <NA> NA
## 1116 <NA> NA
## 1117 <NA> NA
## 1118 <NA> NA
## 1119 <NA> NA
## 1120 <NA> NA
## 1121 <NA> NA
## 1122 <NA> NA
## 1123 <NA> NA
## 1124 <NA> NA
## 1125 <NA> NA
## 1126 <NA> NA
## 1127 <NA> NA
## 1128 <NA> NA
## 1129 <NA> NA
## 1130 <NA> NA
## 1131 <NA> NA
## 1132 <NA> NA
## 1133 <NA> NA
## 1134 <NA> NA
## 1135 <NA> NA
## 1136 <NA> NA
## 1137 <NA> NA
## 1138 <NA> NA
## 1139 <NA> NA
## 1140 <NA> NA
## 1141 <NA> NA
## 1142 <NA> NA
## 1143 <NA> NA
## 1144 <NA> NA
## 1145 <NA> NA
## 1146 <NA> NA
## 1147 <NA> NA
## 1148 <NA> NA
## 1149 <NA> NA
## 1150 <NA> NA
## 1151 <NA> NA
## 1152 <NA> NA
## 1153 <NA> NA
## 1154 <NA> NA
## 1155 <NA> NA
## 1156 <NA> NA
## 1157 <NA> NA
## 1158 <NA> NA
## 1159 <NA> NA
## 1160 <NA> NA
## 1161 <NA> NA
## 1162 <NA> NA
## 1163 <NA> NA
## 1164 <NA> NA
## 1165 <NA> NA
## 1166 <NA> NA
## 1167 <NA> NA
## 1168 <NA> NA
## 1169 <NA> NA
## 1170 <NA> NA
## 1171 <NA> NA
## 1172 <NA> NA
## 1173 <NA> NA
## 1174 <NA> NA
## 1175 <NA> NA
## 1176 <NA> NA
## 1177 <NA> NA
## 1178 <NA> NA
## 1179 <NA> NA
## 1180 <NA> NA
## 1181 <NA> NA
## 1182 <NA> NA
## 1183 <NA> NA
## 1184 <NA> NA
## 1185 <NA> NA
## 1186 <NA> NA
## 1187 <NA> NA
## 1188 <NA> NA
## 1189 <NA> NA
## 1190 <NA> NA
## 1191 <NA> NA
## 1192 <NA> NA
## 1193 <NA> NA
## 1194 <NA> NA
## 1195 <NA> NA
## 1196 <NA> NA
## 1197 <NA> NA
## 1198 <NA> NA
## 1199 <NA> NA
## 1200 <NA> NA
## 1201 <NA> NA
## 1202 <NA> NA
## 1203 <NA> NA
## 1204 <NA> NA
## 1205 <NA> NA
## 1206 <NA> NA
## 1207 <NA> NA
## 1208 <NA> NA
## 1209 <NA> NA
## 1210 <NA> NA
## 1211 <NA> NA
## 1212 <NA> NA
## 1213 <NA> NA
## 1214 <NA> NA
## 1215 <NA> NA
## 1216 <NA> NA
## 1217 <NA> NA
## 1218 <NA> NA
## 1219 <NA> NA
## 1220 <NA> NA
## 1221 <NA> NA
## 1222 <NA> NA
## 1223 <NA> NA
## 1224 <NA> NA
## 1225 <NA> NA
## 1226 <NA> NA
## 1227 <NA> NA
## 1228 <NA> NA
## 1229 <NA> NA
## 1230 <NA> NA
## 1231 <NA> NA
## 1232 <NA> NA
## 1233 <NA> NA
## 1234 <NA> NA
## 1235 <NA> NA
## 1236 <NA> NA
## 1237 <NA> NA
## 1238 <NA> NA
## 1239 <NA> NA
## 1240 <NA> NA
## 1241 <NA> NA
## 1242 <NA> NA
## 1243 <NA> NA
## 1244 <NA> NA
## 1245 <NA> NA
## 1246 <NA> NA
## 1247 <NA> NA
## 1248 <NA> NA
## 1249 <NA> NA
## 1250 <NA> NA
## 1251 <NA> NA
## 1252 <NA> NA
## 1253 <NA> NA
## 1254 <NA> NA
## 1255 <NA> NA
## 1256 <NA> NA
## 1257 <NA> NA
## 1258 <NA> NA
## 1259 <NA> NA
## 1260 <NA> NA
## 1261 <NA> NA
## 1262 <NA> NA
## 1263 <NA> NA
## 1264 <NA> NA
## 1265 <NA> NA
## 1266 <NA> NA
## 1267 <NA> NA
## 1268 <NA> NA
## 1269 <NA> NA
## 1270 <NA> NA
## 1271 <NA> NA
## 1272 <NA> NA
## 1273 <NA> NA
## 1274 <NA> NA
## 1275 <NA> NA
## 1276 <NA> NA
## 1277 <NA> NA
## 1278 <NA> NA
## 1279 <NA> NA
## 1280 <NA> NA
## 1281 <NA> NA
## 1282 <NA> NA
## 1283 <NA> NA
## 1284 <NA> NA
## 1285 <NA> NA
## 1286 <NA> NA
## 1287 <NA> NA
## 1288 <NA> NA
## 1289 <NA> NA
## 1290 <NA> NA
## 1291 <NA> NA
## 1292 <NA> NA
## 1293 <NA> NA
## 1294 <NA> NA
## 1295 <NA> NA
## 1296 <NA> NA
## 1297 <NA> NA
## 1298 <NA> NA
## 1299 <NA> NA
## 1300 <NA> NA
## 1301 <NA> NA
## 1302 <NA> NA
## 1303 <NA> NA
## 1304 <NA> NA
## 1305 <NA> NA
## 1306 <NA> NA
## 1307 <NA> NA
## 1308 <NA> NA
## 1309 <NA> NA
## 1310 <NA> NA
## 1311 <NA> NA
## 1312 <NA> NA
## 1313 <NA> NA
## 1314 <NA> NA
## 1315 <NA> NA
## 1316 <NA> NA
## 1317 <NA> NA
## 1318 <NA> NA
## 1319 <NA> NA
## 1320 <NA> NA
## 1321 <NA> NA
## 1322 <NA> NA
## 1323 <NA> NA
## 1324 <NA> NA
## 1325 <NA> NA
## 1326 <NA> NA
## 1327 <NA> NA
## 1328 <NA> NA
## 1329 <NA> NA
## 1330 <NA> NA
## 1331 <NA> NA
## 1332 <NA> NA
## 1333 <NA> NA
## 1334 <NA> NA
## 1335 <NA> NA
## 1336 <NA> NA
## 1337 <NA> NA
## 1338 <NA> NA
## 1339 <NA> NA
## 1340 <NA> NA
## 1341 <NA> NA
## 1342 <NA> NA
## 1343 <NA> NA
## 1344 <NA> NA
## 1345 <NA> NA
## 1346 <NA> NA
## 1347 <NA> NA
## 1348 <NA> NA
## 1349 <NA> NA
## 1350 <NA> NA
## 1351 <NA> NA
## 1352 <NA> NA
## 1353 <NA> NA
## 1354 <NA> NA
## 1355 <NA> NA
## 1356 <NA> NA
## 1357 <NA> NA
## 1358 <NA> NA
## 1359 <NA> NA
## 1360 <NA> NA
## 1361 <NA> NA
## 1362 <NA> NA
## 1363 <NA> NA
## 1364 <NA> NA
## 1365 <NA> NA
## 1366 <NA> NA
## 1367 <NA> NA
## 1368 <NA> NA
## 1369 <NA> NA
## 1370 <NA> NA
## 1371 <NA> NA
## 1372 <NA> NA
## 1373 <NA> NA
## 1374 <NA> NA
## 1375 <NA> NA
## 1376 <NA> NA
## 1377 <NA> NA
## 1378 <NA> NA
## 1379 <NA> NA
## 1380 <NA> NA
## 1381 <NA> NA
## 1382 <NA> NA
## 1383 <NA> NA
## 1384 <NA> NA
## 1385 <NA> NA
## 1386 <NA> NA
## 1387 <NA> NA
## 1388 <NA> NA
## 1389 <NA> NA
## 1390 <NA> NA
## 1391 <NA> NA
## 1392 <NA> NA
## 1393 <NA> NA
## 1394 <NA> NA
## 1395 <NA> NA
## 1396 <NA> NA
## 1397 <NA> NA
## 1398 <NA> NA
## 1399 <NA> NA
## 1400 <NA> NA
## 1401 <NA> NA
## 1402 <NA> NA
## 1403 <NA> NA
## 1404 <NA> NA
## 1405 <NA> NA
## 1406 <NA> NA
## 1407 <NA> NA
## 1408 <NA> NA
## 1409 <NA> NA
## 1410 <NA> NA
## 1411 <NA> NA
## 1412 <NA> NA
## 1413 <NA> NA
## 1414 <NA> NA
## 1415 <NA> NA
## 1416 <NA> NA
## 1417 <NA> NA
## 1418 <NA> NA
## 1419 <NA> NA
## 1420 <NA> NA
## 1421 <NA> NA
## 1422 <NA> NA
## 1423 <NA> NA
## 1424 <NA> NA
## 1425 <NA> NA
## 1426 <NA> NA
## 1427 <NA> NA
## 1428 <NA> NA
## 1429 <NA> NA
## 1430 <NA> NA
## 1431 <NA> NA
## 1432 <NA> NA
## 1433 <NA> NA
## 1434 <NA> NA
## 1435 <NA> NA
## 1436 <NA> NA
## 1437 <NA> NA
## 1438 <NA> NA
## 1439 <NA> NA
## 1440 <NA> NA
## 1441 <NA> NA
## 1442 <NA> NA
## 1443 <NA> NA
## 1444 <NA> NA
## 1445 <NA> NA
## 1446 <NA> NA
## 1447 <NA> NA
## 1448 <NA> NA
## 1449 <NA> NA
## 1450 <NA> NA
## 1451 <NA> NA
## 1452 <NA> NA
## 1453 <NA> NA
## 1454 <NA> NA
## 1455 <NA> NA
## 1456 <NA> NA
## 1457 <NA> NA
## 1458 <NA> NA
## 1459 <NA> NA
## 1460 <NA> NA
## 1461 <NA> NA
## 1462 <NA> NA
## 1463 <NA> NA
## 1464 <NA> NA
## 1465 <NA> NA
## 1466 <NA> NA
## 1467 <NA> NA
## 1468 <NA> NA
## 1469 <NA> NA
## 1470 <NA> NA
## 1471 <NA> NA
## 1472 <NA> NA
## 1473 <NA> NA
## 1474 <NA> NA
## 1475 <NA> NA
## 1476 <NA> NA
## 1477 <NA> NA
## 1478 <NA> NA
## 1479 <NA> NA
## 1480 <NA> NA
## 1481 <NA> NA
## 1482 <NA> NA
## 1483 <NA> NA
## 1484 <NA> NA
## 1485 <NA> NA
## 1486 <NA> NA
## 1487 <NA> NA
## 1488 <NA> NA
## 1489 <NA> NA
## 1490 <NA> NA
## 1491 <NA> NA
## 1492 <NA> NA
## 1493 <NA> NA
## 1494 <NA> NA
## 1495 <NA> NA
## 1496 <NA> NA
## 1497 <NA> NA
## 1498 <NA> NA
## 1499 <NA> NA
## 1500 <NA> NA
## 1501 <NA> NA
## 1502 <NA> NA
## 1503 <NA> NA
## 1504 <NA> NA
## 1505 <NA> NA
## 1506 <NA> NA
## 1507 <NA> 0
## 1508 <NA> NA
## 1509 <NA> NA
## 1510 <NA> NA
## 1511 <NA> NA
## 1512 <NA> NA
## 1513 <NA> NA
## 1514 <NA> NA
## 1515 <NA> NA
## 1516 <NA> NA
## 1517 <NA> NA
## 1518 <NA> NA
## 1519 <NA> NA
## 1520 <NA> NA
## 1521 <NA> NA
## 1522 <NA> NA
## 1523 <NA> NA
## 1524 <NA> NA
## 1525 <NA> NA
## 1526 <NA> NA
## 1527 <NA> NA
## 1528 <NA> NA
## 1529 <NA> NA
## 1530 <NA> NA
## 1531 <NA> NA
## 1532 <NA> NA
## 1533 <NA> NA
## 1534 <NA> NA
## 1535 <NA> NA
## 1536 <NA> NA
## 1537 <NA> NA
## 1538 <NA> NA
## 1539 <NA> NA
## 1540 <NA> NA
## 1541 <NA> NA
## 1542 <NA> NA
## 1543 <NA> NA
## 1544 <NA> NA
## 1545 <NA> NA
## 1546 <NA> NA
## 1547 <NA> NA
## 1548 <NA> NA
## 1549 <NA> NA
## 1550 <NA> NA
## 1551 <NA> NA
## 1552 <NA> NA
## 1553 <NA> NA
## 1554 <NA> NA
## 1555 <NA> NA
## 1556 <NA> NA
## 1557 <NA> NA
## 1558 <NA> NA
## 1559 <NA> 0
## 1560 <NA> NA
## 1561 <NA> NA
## 1562 <NA> NA
## 1563 <NA> NA
## 1564 <NA> NA
## 1565 <NA> NA
## 1566 <NA> NA
## 1567 <NA> NA
## 1568 <NA> NA
## 1569 <NA> NA
## 1570 <NA> NA
## 1571 <NA> 0
## 1572 <NA> 0
## 1573 <NA> 0
## 1574 <NA> 0
## 1575 <NA> 0
## 1576 <NA> 0
## 1577 <NA> 0
## 1578 <NA> NA
## 1579 <NA> NA
## 1580 <NA> 0
## 1581 <NA> NA
## 1582 <NA> 0
## 1583 <NA> NA
## 1584 <NA> NA
## 1585 <NA> 0
## 1586 <NA> 0
## 1587 <NA> 0
## 1588 <NA> 0
## 1589 <NA> NA
## 1590 <NA> NA
## 1591 <NA> 0
## 1592 <NA> NA
## 1593 <NA> NA
## 1594 <NA> 0
## 1595 <NA> 0
## 1596 <NA> NA
## 1597 <NA> NA
## 1598 <NA> 0
## 1599 <NA> 0
## 1600 <NA> NA
## 1601 <NA> 0
## 1602 <NA> NA
## 1603 <NA> NA
## 1604 <NA> NA
## 1605 <NA> 0
## 1606 <NA> 0
## 1607 <NA> 0
## 1608 <NA> 0
## 1609 <NA> 0
## 1610 <NA> 0
## 1611 <NA> 0
## 1612 <NA> NA
## 1613 <NA> 0
## 1614 <NA> 0
## 1615 <NA> 0
## 1616 <NA> 0
## 1617 <NA> NA
## 1618 <NA> 0
## 1619 <NA> 0
## 1620 <NA> 0
## 1621 <NA> NA
## 1622 <NA> NA
## 1623 <NA> NA
## 1624 <NA> 0
## 1625 <NA> 0
## 1626 <NA> 0
## 1627 <NA> 0
## 1628 <NA> 0
## 1629 <NA> NA
## 1630 <NA> 0
## 1631 <NA> 0
## 1632 <NA> NA
## 1633 <NA> 0
## 1634 <NA> 0
## 1635 <NA> 0
## 1636 <NA> 0
## 1637 <NA> NA
## 1638 <NA> NA
## 1639 <NA> NA
## 1640 <NA> 0
## 1641 <NA> NA
## 1642 <NA> NA
## 1643 <NA> NA
## 1644 <NA> NA
## 1645 <NA> NA
## 1646 <NA> NA
## 1647 <NA> 0
## 1648 <NA> 0
## 1649 <NA> 0
## 1650 <NA> 0
## 1651 <NA> 0
## 1652 <NA> 0
## 1653 <NA> 0
## 1654 <NA> 0
## 1655 <NA> 0
## 1656 <NA> 0
## 1657 <NA> NA
## 1658 <NA> 0
## 1659 <NA> 0
## 1660 <NA> NA
## 1661 <NA> 0
## 1662 <NA> 0
## 1663 <NA> 0
## 1664 <NA> 0
## 1665 <NA> 0
## 1666 <NA> 0
## 1667 <NA> 0
## 1668 <NA> 0
## 1669 <NA> NA
## 1670 <NA> 0
## 1671 <NA> 0
## 1672 <NA> 0
## 1673 <NA> 0
## 1674 <NA> NA
## 1675 <NA> 0
## 1676 <NA> 0
## 1677 <NA> 0
## 1678 <NA> 0
## 1679 <NA> 0
## 1680 <NA> NA
## 1681 <NA> 0
## 1682 <NA> 0
## 1683 <NA> 0
## 1684 <NA> 0
## 1685 <NA> 0
## 1686 <NA> 0
## 1687 <NA> 0
## 1688 <NA> 0
## 1689 <NA> 0
## 1690 <NA> 0
## 1691 <NA> 0
## 1692 <NA> 0
## 1693 <NA> 0
## 1694 <NA> 0
## 1695 <NA> 0
## 1696 <NA> 0
## 1697 <NA> 0
## 1698 <NA> 0
## 1699 <NA> 0
## 1700 <NA> 0
## 1701 <NA> 0
## 1702 <NA> 0
## 1703 <NA> 0
## 1704 <NA> NA
## 1705 <NA> 0
## 1706 <NA> 0
## 1707 <NA> 0
## 1708 <NA> 0
## 1709 <NA> 0
## 1710 <NA> NA
## 1711 <NA> 0
## 1712 <NA> 0
## 1713 <NA> 0
## 1714 <NA> NA
## 1715 <NA> 0
## 1716 <NA> 0
## 1717 <NA> 0
## 1718 <NA> 0
## 1719 <NA> 0
## 1720 <NA> NA
## 1721 <NA> 0
## 1722 <NA> 0
## 1723 <NA> 0
## 1724 <NA> 0
## 1725 <NA> 0
## 1726 <NA> 0
## 1727 <NA> 0
## 1728 <NA> 0
## 1729 <NA> NA
## 1730 <NA> 0
## 1731 <NA> 0
## 1732 <NA> NA
## 1733 <NA> 0
## 1734 <NA> 0
## 1735 <NA> 0
## 1736 <NA> 0
## 1737 <NA> 0
## 1738 <NA> 0
## 1739 <NA> 0
## 1740 <NA> 0
## 1741 <NA> NA
## 1742 <NA> 0
## 1743 <NA> 0
## 1744 <NA> 0
## 1745 <NA> NA
## 1746 <NA> 0
## 1747 <NA> 0
## 1748 <NA> NA
## 1749 <NA> 0
## 1750 <NA> 0
## 1751 <NA> 0
## 1752 <NA> 0
## 1753 <NA> 0
## 1754 <NA> 0
## 1755 <NA> 0
## 1756 <NA> 0
## 1757 <NA> 0
## 1758 <NA> 0
## 1759 <NA> 0
## 1760 <NA> 0
## 1761 <NA> 0
## 1762 <NA> 0
## 1763 <NA> NA
## 1764 <NA> 0
## 1765 <NA> 0
## 1766 <NA> 0
## 1767 <NA> 0
## 1768 <NA> 0
## 1769 <NA> 0
## 1770 <NA> NA
## 1771 <NA> 0
## 1772 <NA> 0
## 1773 <NA> 0
## 1774 <NA> 0
## 1775 <NA> 0
## 1776 <NA> NA
## 1777 <NA> 0
## 1778 <NA> 0
## 1779 <NA> 0
## 1780 <NA> NA
## 1781 <NA> 0
## 1782 <NA> 0
## 1783 <NA> 0
## 1784 <NA> 0
## 1785 <NA> 0
## 1786 <NA> 0
## 1787 <NA> 0
## 1788 <NA> 0
## 1789 <NA> 0
## 1790 <NA> 0
## 1791 <NA> 0
## 1792 <NA> 0
## 1793 <NA> 0
## 1794 <NA> NA
## 1795 <NA> 0
## 1796 <NA> 0
## 1797 <NA> 0
## 1798 <NA> 0
## 1799 <NA> 0
## 1800 <NA> NA
## 1801 <NA> 0
## 1802 <NA> 0
## 1803 <NA> 0
## 1804 <NA> 0
## 1805 <NA> 0
## 1806 <NA> 0
## 1807 <NA> 0
## 1808 <NA> 0
## 1809 <NA> 0
## 1810 <NA> 0
## 1811 <NA> 0
## 1812 <NA> 0
## 1813 <NA> 0
## 1814 <NA> 0
## 1815 <NA> NA
## 1816 <NA> 0
## 1817 <NA> 0
## 1818 <NA> 0
## 1819 <NA> 0
## 1820 <NA> 0
## 1821 <NA> 0
## 1822 <NA> 0
## 1823 <NA> 0
## 1824 <NA> 0
## 1825 <NA> NA
## 1826 <NA> 0
## 1827 <NA> 0
## 1828 <NA> 0
## 1829 <NA> 0
## 1830 <NA> 0
## 1831 <NA> 0
## 1832 <NA> 0
## 1833 <NA> 0
## 1834 <NA> 0
## 1835 <NA> 0
## 1836 <NA> 0
## 1837 <NA> 0
## 1838 <NA> 0
## 1839 <NA> 0
## 1840 <NA> NA
## 1841 <NA> NA
## 1842 <NA> 0
## 1843 <NA> 0
## 1844 <NA> 0
## 1845 <NA> 0
## 1846 <NA> 0
## 1847 <NA> 0
## 1848 <NA> 0
## 1849 <NA> 0
## 1850 <NA> NA
## 1851 <NA> 0
## 1852 <NA> 0
## 1853 <NA> 0
## 1854 <NA> 0
## 1855 <NA> 0
## 1856 <NA> NA
## 1857 <NA> NA
## 1858 <NA> NA
## 1859 <NA> 0
## 1860 <NA> 0
## 1861 <NA> 0
## 1862 <NA> 0
## 1863 <NA> 0
## 1864 <NA> NA
## 1865 <NA> 0
## 1866 <NA> 0
## 1867 <NA> 0
## 1868 <NA> 0
## 1869 <NA> 0
## 1870 <NA> 0
## 1871 <NA> 0
## 1872 <NA> NA
## 1873 <NA> 0
## 1874 <NA> NA
## 1875 <NA> NA
## 1876 <NA> 0
## 1877 <NA> 0
## 1878 <NA> 0
## 1879 <NA> 0
## 1880 <NA> 0
## 1881 <NA> 0
## 1882 <NA> 0
## 1883 <NA> 0
## 1884 <NA> 0
## 1885 <NA> NA
## 1886 <NA> 0
## 1887 <NA> 0
## 1888 <NA> 0
## 1889 <NA> 0
## 1890 <NA> 0
## 1891 <NA> 0
## 1892 <NA> 0
## 1893 <NA> NA
## 1894 <NA> NA
## 1895 <NA> NA
## 1896 <NA> NA
## 1897 <NA> NA
## 1898 <NA> NA
## 1899 <NA> NA
## 1900 <NA> 0
## 1901 <NA> NA
## 1902 <NA> NA
## 1903 <NA> NA
## 1904 <NA> NA
## 1905 <NA> NA
## 1906 <NA> NA
## 1907 <NA> NA
## 1908 <NA> NA
## 1909 <NA> NA
## 1910 <NA> NA
## 1911 <NA> NA
## 1912 <NA> NA
## 1913 <NA> NA
## 1914 <NA> NA
## 1915 <NA> NA
## 1916 <NA> NA
## 1917 <NA> NA
## 1918 <NA> NA
## 1919 <NA> NA
## 1920 <NA> NA
## 1921 <NA> NA
## 1922 <NA> NA
## 1923 <NA> NA
## 1924 <NA> NA
## 1925 <NA> NA
## 1926 <NA> NA
## 1927 <NA> NA
## 1928 <NA> NA
## 1929 <NA> NA
## 1930 <NA> NA
## 1931 <NA> NA
## 1932 <NA> NA
## 1933 <NA> NA
## 1934 <NA> NA
## 1935 <NA> NA
## 1936 <NA> NA
## 1937 <NA> NA
## 1938 <NA> NA
## 1939 <NA> NA
## 1940 <NA> NA
## 1941 <NA> NA
## 1942 <NA> NA
## 1943 <NA> NA
## 1944 <NA> NA
## 1945 <NA> NA
## 1946 <NA> NA
## 1947 <NA> NA
## 1948 <NA> NA
## 1949 <NA> NA
## 1950 <NA> NA
## 1951 <NA> NA
## 1952 <NA> NA
## 1953 <NA> NA
## 1954 <NA> NA
## 1955 <NA> NA
## 1956 <NA> NA
## 1957 <NA> NA
## 1958 <NA> NA
## 1959 <NA> NA
## 1960 <NA> NA
## 1961 <NA> NA
## 1962 <NA> NA
## 1963 <NA> NA
## 1964 <NA> NA
## 1965 <NA> NA
## 1966 <NA> NA
## 1967 <NA> NA
## 1968 <NA> NA
## 1969 <NA> NA
## 1970 <NA> NA
## 1971 <NA> NA
## 1972 <NA> NA
## 1973 <NA> NA
## 1974 <NA> NA
## 1975 <NA> NA
## 1976 <NA> NA
## 1977 <NA> NA
## 1978 <NA> NA
## 1979 <NA> NA
## 1980 <NA> NA
## 1981 <NA> NA
## 1982 <NA> NA
## 1983 <NA> NA
## 1984 <NA> NA
## 1985 <NA> NA
## 1986 <NA> NA
## 1987 <NA> NA
## 1988 <NA> NA
## 1989 <NA> NA
## 1990 <NA> NA
## 1991 <NA> NA
## 1992 <NA> NA
## 1993 <NA> NA
## 1994 <NA> NA
## 1995 <NA> NA
## 1996 <NA> NA
## 1997 <NA> NA
## 1998 <NA> NA
## 1999 <NA> NA
## 2000 <NA> NA
## 2001 <NA> NA
## 2002 <NA> NA
## 2003 <NA> NA
## 2004 <NA> NA
## 2005 <NA> 0
## 2006 <NA> NA
## 2007 <NA> NA
## 2008 <NA> NA
## 2009 <NA> NA
## 2010 <NA> NA
## 2011 <NA> NA
## 2012 <NA> NA
## 2013 <NA> NA
## 2014 <NA> NA
## 2015 <NA> 0
## 2016 <NA> NA
## 2017 <NA> NA
## 2018 <NA> NA
## 2019 <NA> NA
## 2020 <NA> 0
## 2021 <NA> 0
## 2022 <NA> 0
## 2023 <NA> NA
## 2024 <NA> NA
## 2025 <NA> 0
## 2026 <NA> 0
## 2027 <NA> NA
## 2028 <NA> 0
## 2029 <NA> 0
## 2030 <NA> 0
## 2031 <NA> 0
## 2032 <NA> NA
## 2033 <NA> NA
## 2034 <NA> 0
## 2035 <NA> NA
## 2036 <NA> NA
## 2037 <NA> NA
## 2038 <NA> NA
## 2039 <NA> 0
## 2040 <NA> 0
## 2041 <NA> NA
## 2042 <NA> NA
## 2043 <NA> 0
## 2044 <NA> 0
## 2045 <NA> NA
## 2046 <NA> NA
## 2047 <NA> NA
## 2048 <NA> NA
## 2049 <NA> NA
## 2050 <NA> 0
## 2051 <NA> 0
## 2052 <NA> 0
## 2053 <NA> NA
## 2054 <NA> 0
## 2055 <NA> 0
## 2056 <NA> 0
## 2057 <NA> 0
## 2058 <NA> NA
## 2059 <NA> NA
## 2060 <NA> NA
## 2061 <NA> 0
## 2062 <NA> NA
## 2063 <NA> 0
## 2064 <NA> 0
## 2065 <NA> 0
## 2066 <NA> NA
## 2067 <NA> 0
## 2068 <NA> 0
## 2069 <NA> NA
## 2070 <NA> 0
## 2071 <NA> NA
## 2072 <NA> NA
## 2073 <NA> 0
## 2074 <NA> 0
## 2075 <NA> 0
## 2076 <NA> 0
## 2077 <NA> 0
## 2078 <NA> NA
## 2079 <NA> 0
## 2080 <NA> NA
## 2081 <NA> NA
## 2082 <NA> 0
## 2083 <NA> 0
## 2084 <NA> 0
## 2085 <NA> 0
## 2086 <NA> 0
## 2087 <NA> 0
## 2088 <NA> 0
## 2089 <NA> NA
## 2090 <NA> NA
## 2091 <NA> NA
## 2092 <NA> 0
## 2093 <NA> NA
## 2094 <NA> 0
## 2095 <NA> 0
## 2096 <NA> 0
## 2097 <NA> 0
## 2098 <NA> NA
## 2099 <NA> 0
## 2100 <NA> 0
## 2101 <NA> NA
## 2102 <NA> 0
## 2103 <NA> 0
## 2104 <NA> NA
## 2105 <NA> NA
## 2106 <NA> NA
## 2107 <NA> NA
## 2108 <NA> 0
## 2109 <NA> 0
## 2110 <NA> 0
## 2111 <NA> 0
## 2112 <NA> 0
## 2113 <NA> NA
## 2114 <NA> 0
## 2115 <NA> 0
## 2116 <NA> 0
## 2117 <NA> 0
## 2118 <NA> 0
## 2119 <NA> 0
## 2120 <NA> 0
## 2121 <NA> NA
## 2122 <NA> NA
## 2123 <NA> NA
## 2124 <NA> NA
## 2125 <NA> NA
## 2126 <NA> NA
## 2127 <NA> 0
## 2128 <NA> NA
## 2129 <NA> 0
## 2130 <NA> NA
## 2131 <NA> 0
## 2132 <NA> 0
## 2133 <NA> 0
## 2134 <NA> NA
## 2135 <NA> NA
## 2136 <NA> NA
## 2137 <NA> 0
## 2138 <NA> 0
## 2139 <NA> NA
## 2140 <NA> 0
## 2141 <NA> NA
## 2142 <NA> NA
## 2143 <NA> 0
## 2144 <NA> 0
## 2145 <NA> 0
## 2146 <NA> 0
## 2147 <NA> NA
## 2148 <NA> NA
## 2149 <NA> 0
## 2150 <NA> NA
## 2151 <NA> NA
## 2152 <NA> NA
## 2153 <NA> NA
## 2154 <NA> NA
## 2155 <NA> 0
## 2156 <NA> NA
## 2157 <NA> 0
## 2158 <NA> 0
## 2159 <NA> 0
## 2160 <NA> NA
## 2161 <NA> NA
## 2162 <NA> 0
## 2163 <NA> NA
## 2164 <NA> NA
## 2165 <NA> 0
## 2166 <NA> 0
## 2167 <NA> NA
## 2168 <NA> NA
## 2169 <NA> NA
## 2170 <NA> 0
## 2171 <NA> NA
## 2172 <NA> NA
## 2173 <NA> 0
## 2174 <NA> 0
## 2175 <NA> 0
## 2176 <NA> NA
## 2177 <NA> 0
## 2178 <NA> 0
## 2179 <NA> NA
## 2180 <NA> NA
## 2181 <NA> NA
## 2182 <NA> NA
## 2183 <NA> NA
## 2184 <NA> 0
## 2185 <NA> 0
## 2186 <NA> 0
## 2187 <NA> 0
## 2188 <NA> NA
## 2189 <NA> NA
## 2190 <NA> NA
## 2191 <NA> NA
## 2192 <NA> NA
## 2193 <NA> NA
## 2194 <NA> NA
## 2195 <NA> 0
## 2196 <NA> NA
## 2197 <NA> 0
## 2198 <NA> 0
## 2199 <NA> NA
## 2200 <NA> NA
## 2201 <NA> NA
## 2202 <NA> NA
## 2203 <NA> NA
## 2204 <NA> NA
## 2205 <NA> 0
## 2206 <NA> 0
## 2207 <NA> 0
## 2208 <NA> NA
## 2209 <NA> NA
## 2210 <NA> NA
## 2211 <NA> NA
## 2212 <NA> NA
## 2213 <NA> NA
## 2214 <NA> 0
## 2215 <NA> NA
## 2216 <NA> NA
## 2217 <NA> NA
## 2218 <NA> NA
## 2219 <NA> 0
## 2220 <NA> 0
## 2221 <NA> NA
## 2222 <NA> NA
## 2223 <NA> NA
## 2224 <NA> NA
## 2225 <NA> 0
## 2226 <NA> 0
## 2227 <NA> NA
## 2228 <NA> NA
## 2229 <NA> 0
## 2230 <NA> 0
## 2231 <NA> NA
## 2232 <NA> 0
## 2233 <NA> NA
## 2234 <NA> NA
## 2235 <NA> NA
## 2236 <NA> NA
## 2237 <NA> 0
## 2238 <NA> NA
## 2239 <NA> NA
## 2240 <NA> NA
## 2241 <NA> NA
## 2242 <NA> 0
## 2243 <NA> 0
## 2244 <NA> 0
## 2245 <NA> NA
## 2246 <NA> 0
## 2247 <NA> 0
## 2248 <NA> NA
## 2249 <NA> 0
## 2250 <NA> NA
## 2251 <NA> NA
## 2252 <NA> NA
## 2253 <NA> NA
## 2254 <NA> NA
## 2255 <NA> 0
## 2256 <NA> 0
## 2257 <NA> NA
## 2258 <NA> 0
## 2259 <NA> 0
## 2260 <NA> NA
## 2261 <NA> NA
## 2262 <NA> NA
## 2263 <NA> 0
## 2264 <NA> NA
## 2265 <NA> 0
## 2266 <NA> NA
## 2267 <NA> 0
## 2268 <NA> 0
## 2269 <NA> NA
## 2270 <NA> NA
## 2271 <NA> 0
## 2272 <NA> 0
## 2273 <NA> 0
## 2274 <NA> NA
## 2275 <NA> NA
## 2276 <NA> NA
## 2277 <NA> 0
## 2278 <NA> 0
## 2279 <NA> NA
## 2280 <NA> NA
## 2281 <NA> NA
## 2282 <NA> 0
## 2283 <NA> 0
## 2284 <NA> NA
## 2285 <NA> NA
## 2286 <NA> 0
## 2287 <NA> 0
## 2288 <NA> NA
## 2289 <NA> 0
## 2290 <NA> NA
## 2291 <NA> NA
## 2292 <NA> 0
## 2293 <NA> NA
## 2294 <NA> NA
## 2295 <NA> 0
## 2296 <NA> 0
## 2297 <NA> NA
## 2298 <NA> NA
## 2299 <NA> NA
## 2300 <NA> NA
## 2301 <NA> 0
## 2302 <NA> 0
## 2303 <NA> 0
## 2304 <NA> 0
## 2305 <NA> 0
## 2306 <NA> NA
## 2307 <NA> 0
## 2308 <NA> 0
## 2309 <NA> 0
## 2310 <NA> 0
## 2311 <NA> 0
## 2312 <NA> NA
## 2313 <NA> NA
## 2314 <NA> NA
## 2315 <NA> 0
## 2316 <NA> NA
## 2317 <NA> NA
## 2318 <NA> NA
## 2319 <NA> 0
## 2320 <NA> 0
## 2321 <NA> NA
## 2322 <NA> NA
## 2323 <NA> NA
## 2324 <NA> NA
## 2325 <NA> 0
## 2326 <NA> 0
## 2327 <NA> NA
## 2328 <NA> NA
## 2329 <NA> 0
## 2330 <NA> NA
## 2331 <NA> NA
## 2332 <NA> 0
## 2333 <NA> 0
## 2334 <NA> NA
## 2335 <NA> NA
## 2336 <NA> 0
## 2337 <NA> 0
## 2338 <NA> 0
## 2339 <NA> NA
## 2340 <NA> NA
## 2341 <NA> 0
## 2342 <NA> 0
## 2343 <NA> 0
## 2344 <NA> NA
## 2345 <NA> NA
## 2346 <NA> 0
## 2347 <NA> 0
## 2348 <NA> NA
## 2349 <NA> NA
## 2350 <NA> NA
## 2351 <NA> 0
## 2352 <NA> 0
## 2353 <NA> 0
## 2354 <NA> NA
## 2355 <NA> 0
## 2356 <NA> 0
## 2357 <NA> 0
## 2358 <NA> 0
## 2359 <NA> 0
## 2360 <NA> NA
## 2361 <NA> NA
## 2362 <NA> 0
## 2363 <NA> NA
## 2364 <NA> 0
## 2365 <NA> 0
## 2366 <NA> 0
## 2367 <NA> 0
## 2368 <NA> NA
## 2369 <NA> NA
## 2370 <NA> NA
## 2371 <NA> NA
## 2372 <NA> NA
## 2373 <NA> NA
## 2374 <NA> 0
## 2375 <NA> NA
## 2376 <NA> NA
## 2377 <NA> NA
## 2378 <NA> NA
## 2379 <NA> NA
## 2380 <NA> NA
## 2381 <NA> NA
## 2382 <NA> NA
## 2383 <NA> NA
## 2384 <NA> NA
## 2385 <NA> NA
## 2386 <NA> NA
## 2387 <NA> NA
## 2388 <NA> NA
## 2389 <NA> NA
## 2390 <NA> NA
## 2391 <NA> NA
## 2392 <NA> NA
## 2393 <NA> NA
## 2394 <NA> NA
## 2395 <NA> NA
## 2396 <NA> NA
## 2397 <NA> NA
## 2398 <NA> NA
## 2399 <NA> NA
## 2400 <NA> NA
## 2401 <NA> NA
## 2402 <NA> NA
## 2403 <NA> NA
## 2404 <NA> NA
## 2405 <NA> NA
## 2406 <NA> NA
## 2407 <NA> NA
## 2408 <NA> NA
## 2409 <NA> NA
## 2410 <NA> NA
## 2411 <NA> NA
## 2412 <NA> 0
## 2413 <NA> NA
## 2414 <NA> NA
## 2415 <NA> 0
## 2416 <NA> NA
## 2417 <NA> NA
## 2418 <NA> NA
## 2419 <NA> NA
## 2420 <NA> NA
## 2421 <NA> 0
## 2422 <NA> 0
## 2423 <NA> 0
## 2424 <NA> 0
## 2425 <NA> 0
## 2426 <NA> NA
## 2427 <NA> NA
## 2428 <NA> NA
## 2429 <NA> 0
## 2430 <NA> 0
## 2431 <NA> 0
## 2432 <NA> 0
## 2433 <NA> 0
## 2434 <NA> 0
## 2435 <NA> 0
## 2436 <NA> 0
## 2437 <NA> 0
## 2438 <NA> NA
## 2439 <NA> NA
## 2440 <NA> NA
## 2441 <NA> NA
## 2442 <NA> NA
## 2443 <NA> 0
## 2444 <NA> 0
## 2445 <NA> NA
## 2446 <NA> 0
## 2447 <NA> NA
## 2448 <NA> NA
## 2449 <NA> NA
## 2450 <NA> NA
## 2451 <NA> NA
## 2452 <NA> NA
## 2453 <NA> 0
## 2454 <NA> NA
## 2455 <NA> NA
## 2456 <NA> 0
## 2457 <NA> NA
## 2458 <NA> NA
## 2459 <NA> NA
## 2460 <NA> NA
## 2461 <NA> NA
## 2462 <NA> NA
## 2463 <NA> 0
## 2464 <NA> 0
## 2465 <NA> 0
## 2466 <NA> 0
## 2467 <NA> 0
## 2468 <NA> NA
## 2469 <NA> 0
## 2470 <NA> NA
## 2471 <NA> NA
## 2472 <NA> NA
## 2473 <NA> NA
## 2474 <NA> NA
## 2475 <NA> NA
## 2476 <NA> NA
## 2477 <NA> NA
## 2478 <NA> NA
## 2479 <NA> NA
## 2480 <NA> NA
## 2481 <NA> NA
## 2482 <NA> NA
## 2483 <NA> NA
## 2484 <NA> NA
## 2485 <NA> NA
## 2486 <NA> NA
## 2487 <NA> 0
## 2488 <NA> NA
## 2489 <NA> NA
## 2490 <NA> NA
## 2491 <NA> NA
## 2492 <NA> 0
## 2493 <NA> NA
## 2494 <NA> NA
## 2495 <NA> NA
## 2496 <NA> NA
## 2497 <NA> 0
## 2498 <NA> NA
## 2499 <NA> 0
## 2500 <NA> 0
## 2501 <NA> NA
## 2502 <NA> 0
## 2503 <NA> NA
## 2504 <NA> 0
## 2505 <NA> NA
## 2506 <NA> NA
## 2507 <NA> NA
## 2508 <NA> 0
## 2509 <NA> NA
## 2510 <NA> NA
## 2511 <NA> 0
## 2512 <NA> 0
## 2513 <NA> 0
## 2514 <NA> 0
## 2515 <NA> NA
## 2516 <NA> 0
## 2517 <NA> 0
## 2518 <NA> 0
## 2519 <NA> 0
## 2520 <NA> NA
## 2521 <NA> NA
## 2522 <NA> NA
## 2523 <NA> NA
## 2524 <NA> NA
## 2525 <NA> NA
## 2526 <NA> NA
## 2527 <NA> 0
## 2528 <NA> NA
## 2529 <NA> 0
## 2530 <NA> NA
## 2531 <NA> NA
## 2532 <NA> NA
## 2533 <NA> NA
## 2534 <NA> 0
## 2535 <NA> NA
## 2536 <NA> NA
## 2537 <NA> 0
## 2538 <NA> NA
## 2539 <NA> 0
## 2540 <NA> NA
## 2541 <NA> 0
## 2542 <NA> 0
## 2543 <NA> NA
## 2544 <NA> NA
## 2545 <NA> 0
## 2546 <NA> 0
## 2547 <NA> NA
## 2548 <NA> 0
## 2549 <NA> NA
## 2550 <NA> NA
## 2551 <NA> NA
## 2552 <NA> NA
## 2553 <NA> 0
## 2554 <NA> 0
## 2555 <NA> NA
## 2556 <NA> NA
## 2557 <NA> 0
## 2558 <NA> 0
## 2559 <NA> NA
## 2560 <NA> 0
## 2561 <NA> NA
## 2562 <NA> 0
## 2563 <NA> NA
## 2564 <NA> 0
## 2565 <NA> NA
## 2566 <NA> NA
## 2567 <NA> NA
## 2568 <NA> NA
## 2569 <NA> 0
## 2570 <NA> 0
## 2571 <NA> 0
## 2572 <NA> NA
## 2573 <NA> 0
## 2574 <NA> 0
## 2575 <NA> NA
## 2576 <NA> NA
## 2577 <NA> NA
## 2578 <NA> NA
## 2579 <NA> NA
## 2580 <NA> 0
## 2581 <NA> NA
## 2582 <NA> NA
## 2583 <NA> NA
## 2584 <NA> 0
## 2585 <NA> NA
## 2586 <NA> NA
## 2587 <NA> 0
## 2588 <NA> 0
## 2589 <NA> 0
## 2590 <NA> 0
## 2591 <NA> NA
## 2592 <NA> NA
## 2593 <NA> NA
## 2594 <NA> NA
## 2595 <NA> 0
## 2596 <NA> 0
## 2597 <NA> NA
## 2598 <NA> NA
## 2599 <NA> 0
## 2600 <NA> NA
## 2601 <NA> NA
## 2602 <NA> NA
## 2603 <NA> 0
## 2604 <NA> 0
## 2605 <NA> 0
## 2606 <NA> 0
## 2607 <NA> NA
## 2608 <NA> NA
## 2609 <NA> NA
## 2610 <NA> NA
## 2611 <NA> 0
## 2612 <NA> NA
## 2613 <NA> NA
## 2614 <NA> 0
## 2615 <NA> NA
## 2616 <NA> 0
## 2617 <NA> 0
## 2618 <NA> NA
## 2619 <NA> NA
## 2620 <NA> NA
## 2621 <NA> NA
## 2622 <NA> NA
## 2623 <NA> NA
## 2624 <NA> NAsummary(ssd$hospital_los, useNA = "ifany")## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -6378.81 2.93 5.72 8.94 10.48 36530.32ssd$hospitalLOS_Ranges <- cut(ssd$hospital_los, c(0, 1, 3, 5, 10, 20, 30, 60, 90, 150, 999))
table(ssd$hospitalLOS_Ranges,useNA = "ifany")##
## (0,1] (1,3] (3,5] (5,10] (10,20] (20,30] (30,60]
## 150460 582206 529927 820698 507248 143837 85601
## (60,90] (90,150] (150,999] <NA>
## 12058 4741 2364 3381summary(ssd$icu_los, useNA = "ifany")## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -5.3382 0.8278 1.6104 2.7858 3.0500 824.2104ssd$icuLOS_Ranges <- cut(ssd$icu_los, c(0, 1, 3, 5, 10, 20, 30, 60, 999))
table(ssd$icuLOS_Ranges,useNA = "ifany")##
## (0,1] (1,3] (3,5] (5,10] (10,20] (20,30] (30,60] (60,999]
## 928888 1168923 352746 247099 99566 20292 8379 886
## <NA>
## 15742summary(ssd$ethnicity, useNA = "ifany")## African American Asian Caucasian
## 47920 304105 45050 2152704
## Hispanic Native American Other/Unknown
## 145350 25711 121681ssd <- ssd %>% mutate(ethnicity2=recode_factor(ethnicity,
`Caucasian` = "Caucasian",
`African American` = "African American",
`Hispanic`= "Hispanic",
`Asian` = "Asian",
`Native American` = "Native American",
`Other/Unknown` = "Other/Unknown",
.default = "Other/Unknown"))
summary(ssd$ethnicity2, useNA = "ifany")## Caucasian African American Hispanic Asian
## 2152704 304105 145350 45050
## Native American Other/Unknown
## 25711 169601summary(ssd$gender, useNA = "ifany")## Female Male Other Unknown
## 4896 1309647 1527370 52 556ssd <- ssd %>% mutate(gender2=recode_factor(gender,
`Male` = "Male",
`Female` = "Female",
`Other`= "Other/Unknown",
`Unknown` = "Other/Unknown",
.default = "Other/Unknown"))
summary(ssd$gender2, useNA = "ifany")## Male Female Other/Unknown
## 1527370 1309647 5504ssd<- ssd%>%mutate(hospital_mortality=as.factor(hospital_mortality), hospital_mortality_ultimate=as.factor(hospital_mortality_ultimate), icu_mortality=as.factor(icu_mortality))
ssd <- ssd%>%mutate(hospital_region=as.factor(hospital_region))
summary(ssd$hospital_region)## Midwest Northeast South West
## 632962 753120 165767 714254 576418ssd <- ssd %>% mutate(hospital_region2=recode_factor(hospital_region, 'Midwest' = "Midwest", 'Northeast' = "Northeast", 'South' = "South", 'West' = "West", .default = "Unknown"))
summary(ssd$hospital_region2)## Midwest Northeast South West Unknown
## 753120 165767 714254 576418 6329622 Sepsis Defined
We defined positive for sepsis (in-hospital sepsis) as having either a severe sepsis or septic shock diagnosis or having an infection and an acute organ failure diagnosis in the medical record during a 24-hour period starting from the documented ICU admission date and time. Patients with no diagnoses in the diagnoses
ssd<- ssd %>% mutate(sepsis_outcome = (sepsis >0 | (infection >0 & organfailure >0)))
summary(ssd$sepsis_outcome)## Mode FALSE TRUE NA's
## logical 1906183 485158 451180table(ssd$sepsis_outcome, useNA = "ifany")##
## FALSE TRUE <NA>
## 1906183 485158 4511803 Parsing of APACHE Admit Diagnoses
Parsing of APACHE admission diagnoses into organ system grouper with sepsis diagnoses in separate category. 25 diagnoses were categorized as Undefined with 16 transplant diagnoses and 9 of various other non-specific nature.
parse_dx <- function(x) {
sp <- str_split(as.character(x),"\\|")
idx <- sapply(sp,length)
out <- sapply(1:length(idx),function(v) { return(sp[[v]][idx[v]])})
return(out)
}
ap <- ap %>% mutate(new_apdx =parse_dx(admitdxpath)) %>% group_by(new_apdx) %>% mutate(n=row_number()) %>% ungroup()
nrow(ap)## [1] 448colnames(ap)## [1] "group" "post.operative" "code" "dx"
## [5] "number" "admitdiagnosis" "admitdxpath" "numobs"
## [9] "possible.group" "X" "new_apdx" "n"ssd_j <- ssd %>% left_join(ap%>%filter(n==1)%>%select(-n),by=c("apacheadmissiondx"="new_apdx"))## Warning: Column `apacheadmissiondx`/`new_apdx` joining factor and character
## vector, coercing into character vectornrow(ssd_j)## [1] 2842521if(nrow(ssd_j)==nrow(ssd)) {ssd <- ssd_j;rm(ssd_j)}
nrow(ssd)## [1] 2842521summary(ssd$group, useNA = "ifany")## Cardiovascular Gastrointestinal
## 839352 266781
## Gynaecological Hematological
## 6754 18705
## Metabolic Muscoskeletal/Skin disease
## 193873 35740
## Neurological Other medical disorders
## 323997 0
## Renal/Genitourinary Respiratory
## 61926 381474
## Sepsis Trauma
## 571651 111731
## Undefined NA's
## 21389 9148ssd<-ssd%>%mutate(group=droplevels(group))
summary(ssd$group, useNA = "ifany")## Cardiovascular Gastrointestinal
## 839352 266781
## Gynaecological Hematological
## 6754 18705
## Metabolic Muscoskeletal/Skin disease
## 193873 35740
## Neurological Renal/Genitourinary
## 323997 61926
## Respiratory Sepsis
## 381474 571651
## Trauma Undefined
## 111731 21389
## NA's
## 91484 Defining data variables: as.factor, as.character…
ssd <- ssd%>%mutate(dialysis=as.factor(dialysis),
aids=as.factor(aids),
hepaticfailure=as.factor(hepaticfailure|
cirrhosis),
diabetes=as.factor(diabetes),
immunosuppression=as.factor(immunosuppression),
leukemia=as.factor(leukemia),
lymphoma=as.factor(lymphoma),
metastaticcancer=as.factor(metastaticcancer),
thrombolytics=as.factor(thrombolytics),
cardiovascular_baseline=as.factor(cardiovascular_baseline))
ssd <- ssd%>%mutate(hospitaldischargeyear=as.character(hospitaldischargeyear))
ssd$hospitaldischargeyear[ssd$hospitaldischargeyear<=2010] <- "-2010"
ssd$hospitaldischargeyear[ssd$hospitaldischargeyear>=2015] <- "2015-16"
summary(ssd$hospitaldischargeyear)## Length Class Mode
## 2842521 character characterssd <- ssd%>%mutate(hospital_mortality=as.factor(hospital_mortality), hospital_mortality_ultimate=as.factor(hospital_mortality_ultimate), icu_mortality=as.factor(icu_mortality))5 Medication Variable Decisions
Organ dysfunction criteria are met or ignored when certain medications are present. For example, when warfarin and heparin are present lab values associated with coagulopathies (INR and aPTT) are ignored. Vasopressors are generally ordered for a patient with evidence of hypotension, hypoperfusion, or shock. In this study, patients without activity in the medication tables were excluded. Medication data related to continuous infusions are found in one of two places; the medication table which indicates a medication as being ordered or in the nurse charted table indicating starting and/or titrating a continuous infusion. In the early years many ICUs used the TeleICU EHR (also known as eCareManager) as a clinical documentation system. Overtime as hospitals began to implement more comprehensive EHR solutions nurse charting was interfaced in many but not all ICUs. This is consistent with other studies using the eRI complete dataset.
ssd$dopamine_infusion[is.na(ssd$dopamine_infusion)]<-0
ssd$dopamine_medication[is.na(ssd$dopamine_medication)]<-0
ssd$epinephrine_infusion[is.na(ssd$epinephrine_infusion)]<-0
ssd$epinephrine_medication[is.na(ssd$epinephrine_medication)]<-0
ssd$norepinephrine_infusion[is.na(ssd$norepinephrine_infusion)]<-0
ssd$norepinephrine_medication[is.na(ssd$norepinephrine_medication)]<-0
ssd$milrinone_infusion[is.na(ssd$milrinone_infusion)]<-0
ssd$milrinone_medication[is.na(ssd$milrinone_medication)]<-0
ssd$phenylephrine_infusion[is.na(ssd$phenylephrine_infusion)]<-0
ssd$phenylephrine_medication[is.na(ssd$phenylephrine_medication)]<-0
nrow(ssd)## [1] 28425216 Explanation of vital sign data variable decisions
Vital Sign (VS) data can come from several sources within the dataset. When multiple VS data sources were available within a single patient chart data were selected in this order 1) Charted/validated nurse 2) If no charted VS data were available then by vital signs interfaced from bedside monitor (unvalidated) were used 3) Non-invasive blood pressure (NIBP) data were selected over invasive blood pressure (IBP) data if both were present on the same patient. NIBP readings tend to have less variation than IBP readings. 4) APACHE VS variables are the worst reading from normal based on APACHE data collection methods.
ssd <- ssd %>% mutate(c_temp_min =ifelse (is.na (temperature_charted_min),ifelse(is.na(temperature_min), ifelse(temperature_apache==-1, NA, temperature_apache), temperature_min),temperature_charted_min))
summary(ssd$c_temp_min)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.1 36.1 36.4 36.4 36.7 108.3 319848ssd <- ssd %>% mutate(c_temp_max =if_else (is.na (temperature_charted_max),ifelse(is.na(temperature_max), ifelse(temperature_apache==-1, NA, temperature_apache), temperature_max),temperature_charted_max))
summary(ssd$c_temp_max)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.1 36.8 37.1 37.3 37.6 112.6 319848ssd <- ssd %>% mutate(c_HR_max =ifelse (is.na (heartrate_charted_max),ifelse(is.na(heartrate_max), ifelse(heartrate_apache==-1, NA, heartrate_apache), heartrate_max),heartrate_charted_max))
summary(ssd$c_HR_max)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.0 86.0 99.0 101.4 115.0 387.0 112042ssd <- ssd %>% mutate(c_resp_max =ifelse (is.na (respiratoryrate_charted_max),ifelse(is.na(respiratoryrate_max), ifelse(respiratoryrate_apache==-1, NA, respiratoryrate_apache), respiratoryrate_max),respiratoryrate_charted_max))
summary(ssd$c_resp_max)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.00 21.00 25.00 26.98 30.00 200.00 134725ssd <- ssd %>% mutate(c_sbp_min =ifelse (is.na (sbp_charted_min), ifelse(is.na(ibp_systolic_charted_min),nibp_systolic_charted_min, ibp_systolic_charted_min), sbp_charted_min))
summary(ssd$c_sbp_min)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.0 85.0 98.0 99.1 113.0 264.0 702587ssd <- ssd %>% mutate(c_sbp_min =ifelse(is.na(c_sbp_min),(sbp_min),c_sbp_min))
summary(ssd$c_sbp_min)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.00 75.00 92.00 92.01 109.00 347.00 198922ssd <- ssd %>% mutate(c_mbp_min =ifelse (is.na (nibp_mean_charted_min),ifelse(is.na(ibp_mean_charted_min), ifelse(mbp_apache==-1, NA, mbp_apache), ibp_mean_charted_min),nibp_mean_charted_min))
summary(ssd$c_mbp_min)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.13 56.00 66.00 70.12 78.00 359.00 250116ssd <- ssd %>% mutate(c_mbp_min=if_else(is.na(c_mbp_min),(mbp_charted_min),c_mbp_min))
summary(ssd$c_mbp_min)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.13 56.00 66.00 70.12 78.00 359.00 250116ssd %>% filter(is.na (nibp_systolic_charted_min))%>%select(c_sbp_min,ibp_systolic_charted_min)%>%head()## c_sbp_min ibp_systolic_charted_min
## 1 NA NA
## 2 NA NA
## 3 NA NA
## 4 NA NA
## 5 NA NA
## 6 NA NAssd %>% filter(is.na (nibp_mean_charted_min))%>%select(c_mbp_min,ibp_mean_charted_min)%>%head()## c_mbp_min ibp_mean_charted_min
## 1 NA NA
## 2 NA NA
## 3 NA NA
## 4 NA NA
## 5 NA NA
## 6 NA NA7 ICU admit source recoded
Combined the 14 unique choices for source of admission into 6 like categories. NAs were coded as “Other”.
table(ssd$icu_admit_source, useNA = "ifany")##
## Acute Care/Floor Chest Pain Center
## 67402 27695 9943
## Direct Admit Emergency Department Emergency Room
## 175631 1245659 149
## Floor ICU ICU to SDU
## 407519 31038 188944
## Observation Operating Room Other
## 118 367328 65
## Other Hospital Other ICU PACU
## 65765 85071 8412
## Recovery Room Step-Down Unit (SDU)
## 109083 52699ssd <- ssd %>% mutate(icu_admit_source2=recode_factor(icu_admit_source,
`Acute Care/Floor`= "Floor",
`Chest Pain Center` = "OR/Proc Area",
`Direct Admit` = "Direct Admit",
`Emergency Department` = "Emergency Department",
`Floor` = "Floor",
`ICU` = "Other",
`ICU to SDU` = "Step-Down Unit",
`Observation` = "Other",
`Operating Room` = "OR/Proc Area",
`Other` = "Other",
`Other Hospital` = "Direct Admit",
`Other ICU` = "Other",
`PACU` = "OR/Proc Area",
`Recovery Room` = "OR/Proc Area",
`Step-Down Unit (SDU)`= "Step-Down Unit",
.default = "Other"))
table(ssd$icu_admit_source2,useNA = "ifany")##
## Floor OR/Proc Area Direct Admit
## 435214 494766 241396
## Emergency Department Other Step-Down Unit
## 1245659 183843 2416438 ICU Type Decisions
It appears that the names of ICUs have changed over time within the dataset and the names selected by the vendor do not clearly distinguish the type of ICU. We decided to not use the ICU type in Table 1 or in the models for this reason.
ssd <- ssd %>% mutate(icu_type2=recode_factor(icu_type,
`Burn-Trauma ICU`= "Trauma ICU",
`Cardiac ICU`= "Cardiac Care ICU",
`CCU-CTICU` = "Cardiac/Surgical Care ICU",
`CCU` = "Cardiac Care ICU",
`CSICU` = "Cardiac/Surgical Care ICU",
`CTICU` = "Cardiac/Surgical Care ICU",
`Med-Surg ICU` = "Medical/Surgical ICU",
`MICU` = "Medical ICU",
`Mobile ICU` = "Other ICU",
`Neuro ICU` = "Neuro ICU",
`PACU` = "Other ICU",
`SICU` = "Surgical ICU",
`Trauma ICU` = "Trauma ICU",
`Vent ICU` = "Other ICU",
`VICU` = "Other ICU",
`Virtual ICU` = "Other ICU",
.default = "Other ICU"))
table(ssd$icu_type2, useNA = "ifany")##
## Trauma ICU Cardiac Care ICU
## 36823 192048
## Cardiac/Surgical Care ICU Medical/Surgical ICU
## 437527 1527054
## Medical ICU Other ICU
## 248339 56590
## Neuro ICU Surgical ICU
## 164626 179514table(ssd$hospital_size, useNA = "ifany")##
## <100 100-249 250-500 >500
## 643295 141919 533513 481826 10419689 Discharge locations recoded
Combined the 18 unique discharge locations into 7 like categories. NAs were coded as “Other”.
ssd <- ssd %>% mutate(icu_disch_location2=recode_factor(icu_disch_location,
`Acute Care/Floor`= "Floor",
`Death` = "Death",
`Floor` = "Floor",
`Home` = "Home",
`Nursing Home` = "SNF/Rehab",
`ICU` = "Other",
`Other ICU` = "Other",
`Observation` = "Other",
`Operating Room` = "Other",
`Other` = "Other",
`Other External` = "Other",
`Other Internal` = "Floor",
`Other Hospital` = "Other Hospital",
`Other ICU (CABG)` = "Other",
`Rehabilitation` = "SNF/Rehab",
`Skilled Nursing Facility` = "SNF/Rehab",
`Step-Down Unit (SDU)`= "Step-Down Unit",
`Telemetry`= "Floor",
.default = "Other"))
table(ssd$icu_disch_location2,useNA = "ifany")##
## Floor Death Home SNF/Rehab Other
## 1850937 154009 250587 34591 202328
## Other Hospital Step-Down Unit
## 58896 29117310 Physician Specialties recoded
Combined the 48 unique physician specialties into 2 categories (Critical Care or Specialty-Other). Initial analyses in the subset suggested that there was a difference between Critical Care and all other categories. There were no NAs in the subset. There were 17 in the subset categorized as “unknown”; we coded these as “Specialty-Other”.
table(ssd$physicianspeciality,useNA = "ifany")##
## allergy/immunology
## 1010706 590
## anesthesiology anesthesiology/CCM
## 1463 7519
## cardiology critical care medicine (CCM)
## 166439 140776
## dermatology emergency medicine
## 35 8121
## endocrinology ethics
## 1536 13
## family practice gastroenterology
## 85320 6617
## hematology hematology/oncology
## 525 3898
## hospitalist infectious disease
## 259993 2934
## internal medicine nephrology
## 299354 15389
## neurology nurse
## 25726 73
## nurse practitioner obstetrics/gynecology
## 59 7244
## oncology ophthalmology
## 7213 200
## orthopedics other
## 8931 24891
## otolaryngology pain management
## 5658 21
## pharmacist physical medicine/rehab
## 11 208
## psychiatry pulmonary
## 378 71676
## pulmonary/CCM radiology
## 143113 1964
## respiratory therapist rheumatology
## 10 98
## Specialty Not Specified surgery-cardiac
## 142045 73447
## surgery-critical care surgery-general
## 5883 106574
## surgery-neuro surgery-oral
## 52257 253
## surgery-orthopedic surgery-otolaryngology head & neck
## 2551 267
## surgery-pediatric surgery-plastic
## 20 1531
## surgery-transplant surgery-trauma
## 2237 29323
## surgery-vascular unknown
## 31142 80353
## urology
## 5936ssd <- ssd %>% mutate (physicianSpeciality2= droplevels(recode_factor(physicianspeciality,`critical care medicine (CCM)`= "Critical Care",`anesthesiology/CCM`= "Critical Care",`anesthesiology`= "Critical Care",`surgery-critical care` = "Critical Care",`surgery-trauma` = "Critical Care",`surgery-transplant` = "Speciality-Other",`surgery-orthopedic` = "Speciality-Other",`surgery-general` = "Speciality-Other",`surgery-oral` = "Speciality-Other",`surgery-pediatric` = "Speciality-Other",`surgery-otolaryngology head & neck` = "Speciality-Other", `surgery-cardiac` = "Critical Care",`neurology` = "Speciality-Other", `cardiology`= "Speciality-Other", `surgery-neuro` = "Speciality-Other",`surgery-plastic` = "Speciality-Other", `surgery-vascular` = "Speciality-Other", `oncology` = "Speciality-Other", `hematology` = "Speciality-Other", `hematology/oncology` = "Speciality-Other", `family practice` = "Speciality-Other", `internal medicine` = "Speciality-Other", `Specialty Not Specified` = "Speciality-Other",`urology` = "Speciality-Other",`orthopedics`= "Speciality-Other", `nephrology` = "Speciality-Other", `allergy/immunology` = "Speciality-Other",`dermatology` = "Speciality-Other",`endocrinology` = "Speciality-Other",`ethics` = "Speciality-Other",`emergency medicine` = "Speciality-Other",`gastroenterology` = "Speciality-Other",`obstetrics/gynecology` = "Speciality-Other", `nurse practitioner` = "Speciality-Other",`nurse` = "Speciality-Other",`ophthalmology` = "Speciality-Other",`respiratory therapist` = "Speciality-Other", `other` = "Speciality-Other", `specialty other` = "Speciality-Other", `radiology` = "Speciality-Other", `rheumatology` = "Speciality-Other", `rheumatology` = "Speciality-Other",`infectious disease` = "Speciality-Other",`otolaryngology` = "Speciality-Other",`physical medicine/rehab` = "Speciality-Other",`psychiatry` = "Speciality-Other",`unknown` = "Speciality-Other",`pulmonary` = "Critical Care", `pharmacist` = "Speciality-Other", `Medicine-General` = "Speciality-Other", `pain management` = "Speciality-Other", `pulmonary/CCM`= "Critical Care",`hospitalist` = "Speciality-Other", .default = "Speciality-Other")))
table(ssd$physicianSpeciality2,useNA = "ifany") ##
## Critical Care Speciality-Other
## 473200 236932111 Explanation of Fuzzy Logic SIRS/OD, SIRS, SOFA, qSOFA
The sepsis Fuzzy Logic variables are broken up into Fuzzy Logic Systemic Inflammatory Response Syndrome (SIRs) and Fuzzy Logic organ dysfunction (OD). Baseline Sequential Organ Failure Assessment (SOFA) scores were assigned for three chronic health conditions using the same methodology as the ANZICS study: patients with chronic respiratory received 2 baseline points, and chronic hepatic and renal organ failure received 4 baseline points. For cardiovascular as a comorbid condition we used documented past medical history of myocardial infarction, congestive heart failure, and angina. The following comorbid conditions (also used for baseline SOFA scoring) were defined as: 1) for respiratory we used documented past medical history of COPD, respiratory failure, restrictive pulmonary disease, sarcoidosis, status post lung transplant, or abnormal pulmonary function tests; 2) for renal we used documented past medical history of dialysis; 3) for liver we used documented past medical history of hepatic failure or cirrhosis
SOFA organ dysfunction scoring was assigned per SOFA score definitions.
Note: We made a cut for SOFA Change but will need to review this in full dataset. See partition section.
ssd <- ssd %>% mutate (sofa_respiration_baseline2=as.factor(if_else(is.na(sofa_respiration_baseline),FALSE, as.logical(sofa_respiration_baseline))))
ssd <- ssd %>% mutate (sofa_renal_baseline2=as.factor(if_else(is.na(sofa_renal_baseline),FALSE, as.logical(sofa_renal_baseline))))
ssd <- ssd %>% mutate (sofa_liver_baseline2=as.factor(if_else(is.na(sofa_liver_baseline),FALSE, as.logical(sofa_liver_baseline))))
ssd <- ssd %>% mutate(SOFA_Change = (sofa_respiration*(sofa_respiration_baseline!=2) + sofa_coagulation + sofa_liver*(sofa_liver_baseline !=4) + sofa_cardiovascular + sofa_cns + sofa_renal*(sofa_renal_baseline!=4)))
ssd <- ssd %>% mutate(SOFA_Positive = SOFA_Change >=2)
summary(ssd$SOFA_Positive)## Mode FALSE TRUE
## logical 1141836 1700685table(ssd$SOFA_Positive,useNA = "ifany")##
## FALSE TRUE
## 1141836 1700685ssd <- ssd %>% mutate(SOFA_Score = (sofa_respiration + sofa_coagulation + sofa_liver + sofa_cardiovascular + sofa_cns + sofa_renal))
ssd <- ssd %>% mutate(SOFA_Positive2 = SOFA_Score >=2)
summary(ssd$SOFA_Positive2)## Mode FALSE TRUE
## logical 1092979 1749542table(ssd$SOFA_Positive2,useNA = "ifany")##
## FALSE TRUE
## 1092979 1749542ssd <- ssd %>% mutate(GCS_qSOFA = (gcs !=-3& (gcs<15)),
BP_qSOFA = (c_sbp_min <=100),
Resp_qSOFA = (c_resp_max >=22))
ssd <- ssd %>% mutate(qSOFA_total = (if_else(is.na(GCS_qSOFA),FALSE,GCS_qSOFA) + if_else(is.na(BP_qSOFA),FALSE, BP_qSOFA) + if_else(is.na(Resp_qSOFA),FALSE,Resp_qSOFA)))
ssd <- ssd %>% mutate(qSOFA_Positive = qSOFA_total >=2)
summary(ssd$qSOFA_Positive)## Mode FALSE TRUE
## logical 1236207 1606314table(ssd$qSOFA_Positive,useNA = "ifany")##
## FALSE TRUE
## 1236207 1606314ssd <- ssd %>% mutate(temp_SIRS = c_temp_max >38 | c_temp_min<36,
wbc_SIRS = if_else(is.na(wbc_min) & is.na(wbc_max),bands_max>=10,if_else(is.na(bands_max),wbc_max>12 | wbc_min<4,if_else(!is.na(wbc_min)&!is.na(wbc_max)&!is.na(bands_max),wbc_max>12 | wbc_min<4 | bands_max>=10,NA))),
resp_SIRS = if_else(is.na(c_resp_max), paco2_min <32, if_else(is.na(paco2_min), c_resp_max>20, if_else(!is.na(c_resp_max)&!is.na(paco2_min), c_resp_max>20 | paco2_min<32, NA))),
HR_SIRS = c_HR_max >90)
ssd <- ssd %>% mutate(SIRS_total = (if_else(is.na(temp_SIRS),FALSE, temp_SIRS) + if_else(is.na(wbc_SIRS),FALSE, wbc_SIRS) + if_else(is.na(resp_SIRS),FALSE,resp_SIRS) + if_else(is.na(HR_SIRS), FALSE, HR_SIRS)))
table(ssd$SIRS_total,useNA = "ifany")##
## 0 1 2 3 4
## 310612 593666 954052 724089 260102ssd <- ssd %>% mutate(SIRS_Positive = SIRS_total >=2)
table(ssd$SIRS_Positive,useNA = "ifany")##
## FALSE TRUE
## 904278 1938243ssd <- ssd %>% mutate(StickyMinutes = if_else (soi_minutes >= od_minutes, soi_minutes, od_minutes))
ssd <- ssd %>% mutate(FuzzyTotal1 = (if_else(is.na(soi_alpha), 0, 1) + if_else(is.na(od_alpha), 0,1)))
### HERE
table(ssd$FuzzyTotal1,useNA = "ifany")##
## 0 1 2
## 487388 932434 1422699summary(ssd$FuzzyTotal1, useNA = "ifany")## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 1.000 2.000 1.329 2.000 2.000#ssd %>% filter(patientunitstayid == 141289)
nrow(ssd)## [1] 2842521ssd <- ssd %>% mutate(SimultaneousMinutes = !is.na (both_minutes))
summary(ssd$SimultaneousMinutes)## Mode FALSE TRUE
## logical 1523008 1319513ssd <- ssd %>% mutate(SepsisFuzzyLogicPositive= !is.na (both_soi_alpha + both_od_alpha))
table(ssd$SepsisFuzzyLogicPositive,useNA = "ifany")##
## FALSE TRUE
## 1523008 1319513ssd <- ssd%>% mutate(SepsisFuzzyLogicPositive2 = SimultaneousMinutes)12 Inclusion/Exclusion Criteria
The designs and findings from several previous studies using the complete dataset were used identify inclusion and exclusion criteria that would best support decision-making related to missingness and generalizability. To reduce introduction of missingness, patients where no evidence of interfaces or documentation for laboratory, vital sign, medication, and diagnosis related data existed, were excluded (convenience sample). Other similar large data studies made decisions related to imputation to deal with missingness. Limitations of imputation techniques include underestimation of standard errors/overestimation of test statistics, different imputation methods can produce different estimates and some methods can produce different estimates every time they are used on the same dataset, some require specialized software, and some can only be used for linear and log-linear models. Improper handling of missing data can compromise the validity of a study’s results or inferences. Because of the sheer number of cases within the complete dataset, as well as the subset, the researcher was not concerned about losing power. Secondly, patients that show no activity in laboratory, vital sign, medication, and diagnosis tables are not missing data at random but are likely missing because of a lack of interface between hospital information systems and the eCareManager system. Imputing on these cases may introduce the bias that is trying to be avoided Given these reasons a decision was made in advance to exclude cases with no activity in the tables forementioned. Table 1 “Exclusion versus Inclusion Demographic, Severity of Illness, Diagnostic and Sepsis Outcome Date” compares excluded versus included patients.
table(ssd$exclusion_yearfilter)##
## 0 1
## 2020489 822032table(ssd$exclusion_over18)##
## 0 1
## 2830319 12202table(!is.na(ssd$age))##
## FALSE TRUE
## 2061 2840460table(ssd$exclusion_firstadmission)##
## 0 1
## 2369682 472839table(ssd$exclusion_apacheiva)##
## 0 1
## 1768014 1074507table(ssd$exclusion_vitalobservations)##
## 0 1
## 2550796 291725table(ssd$exclusion_labobservations)##
## 0 1
## 2767549 74972table(ssd$exclusion_medobservations)##
## 0 1
## 2413821 428700ssd_incl <- ssd %>% filter(exclusion_yearfilter==0)
nrow(ssd_incl)## [1] 2020489ssd_incl <- ssd_incl %>% filter(exclusion_over18==0 & !is.na(age))
nrow(ssd_incl)## [1] 2011652ssd_incl <- ssd_incl %>% filter(exclusion_firstadmission==0)
nrow(ssd_incl)## [1] 1666917ssd_incl <-ssd_incl %>%filter(exclusion_apacheiva==0)
nrow(ssd_incl)## [1] 1162680ssd_incl <- ssd_incl %>% filter(exclusion_vitalobservations==0)
nrow(ssd_incl)## [1] 1073088ssd_incl <- ssd_incl %>% filter(exclusion_labobservations==0)
nrow(ssd_incl)## [1] 1068937ssd_incl <- ssd_incl %>% filter(exclusion_medobservations==0)
nrow(ssd_incl)## [1] 929538Cases with no activity in the diagnosis table were excluded. Using a binary classification process positive for sepsis (in-hospital sepsis) was defined by having either a severe sepsis or septic shock diagnosis or having an infection and an acute organ failure diagnosis in the medical record during a 24-hour period starting from ICU admission date and time.
ssd_incl$hasDiagnosisCodes <- (!is.na(ssd_incl$sepsis)& !is.na(ssd_incl$organfailure)& !is.na(ssd_incl$infection))
ssd_incl <- ssd_incl %>% filter(hasDiagnosisCodes)
nrow(ssd_incl)## [1] 91250913 Preparation of data variables for Table 1
“Exclusion versus Inclusion Demographic, Severity of Illness, Diagnostic and Sepsis Outcome Date” compares excluded versus included patients.
ssd$hasDiagnosisCodes <- (!is.na(ssd$sepsis)& !is.na(ssd$organfailure)& !is.na(ssd$infection))
table(ssd$hasDiagnosisCodes, useNA = "ifany")##
## FALSE TRUE
## 451180 2391341ssd$inclusiongroup <- 1
ssd$inclusiongroup [ssd$exclusion_over18==1]<- 0
ssd$inclusiongroup [ssd$exclusion_firstadmission==1]<- 0
ssd$inclusiongroup [ssd$exclusion_apacheiva==1]<- 0
ssd$inclusiongroup [ssd$exclusion_yearfilter==1]<- 0
ssd$inclusiongroup [ssd$exclusion_vitalobservations==1]<- 0
ssd$inclusiongroup [ssd$exclusion_labobservations==1]<- 0
ssd$inclusiongroup [ssd$exclusion_medobservations==1]<- 0
ssd$inclusiongroup [!ssd$hasDiagnosisCodes]<- 0
summary(ssd$inclusiongroup, UseNA = "ifany")## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 0.000 0.000 0.321 1.000 1.000table(ssd$inclusiongroup, useNA = "ifany")##
## 0 1
## 1930007 912514ssd %>%group_by(hospitalid)%>%summarise(n=n(), numberincluded=sum(inclusiongroup), numberexcluded=sum(inclusiongroup==0), proportionincluded=numberincluded/n)%>%filter(n>100)%>%ggplot(aes(proportionincluded))+geom_histogram()## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
ssd %>%group_by(hospitalid)%>%summarise(n=n(), numberincluded=sum(inclusiongroup), numberexcluded=sum(inclusiongroup==0), proportionincluded=numberincluded/n)%>%filter(n>100 & proportionincluded<.05)## # A tibble: 130 x 5
## hospitalid n numberincluded numberexcluded proportionincluded
## <int> <int> <dbl> <int> <dbl>
## 1 1 6840 0. 6840 0.
## 2 3 1702 0. 1702 0.
## 3 4 9705 0. 9705 0.
## 4 5 722 0. 722 0.
## 5 6 1768 0. 1768 0.
## 6 7 1164 0. 1164 0.
## 7 8 5523 0. 5523 0.
## 8 9 6087 0. 6087 0.
## 9 12 3538 0. 3538 0.
## 10 13 566 0. 566 0.
## # ... with 120 more rowsssd %>%filter(hospitalid==207)%>%select(contains("exclusion_"),icu_type)%>%summary## exclusion_over18 exclusion_firstadmission exclusion_yearfilter
## Min. :0 Min. :0.0000 Min. :0.00000
## 1st Qu.:0 1st Qu.:0.0000 1st Qu.:0.00000
## Median :0 Median :0.0000 Median :0.00000
## Mean :0 Mean :0.3363 Mean :0.07171
## 3rd Qu.:0 3rd Qu.:1.0000 3rd Qu.:0.00000
## Max. :0 Max. :1.0000 Max. :1.00000
##
## exclusion_apacheiva exclusion_vitalobservations exclusion_labobservations
## Min. :0.0000 Min. :0.00000 Min. :0.00000
## 1st Qu.:0.0000 1st Qu.:0.00000 1st Qu.:0.00000
## Median :1.0000 Median :0.00000 Median :0.00000
## Mean :0.6921 Mean :0.04839 Mean :0.03725
## 3rd Qu.:1.0000 3rd Qu.:0.00000 3rd Qu.:0.00000
## Max. :1.0000 Max. :1.00000 Max. :1.00000
##
## exclusion_medobservations icu_type
## Min. :0.0000 Med-Surg ICU :5712
## 1st Qu.:1.0000 Mobile ICU : 33
## Median :1.0000 Burn-Trauma ICU : 0
## Mean :0.8019 Cardiac ICU : 0
## 3rd Qu.:1.0000 Cardiovascular ICU: 0
## Max. :1.0000 CCU-CTICU : 0
## (Other) : 0ssd %>%filter(hospitalid==207)%>%select(contains("exclusion_"),icu_type, hasDiagnosisCodes)%>%summary## exclusion_over18 exclusion_firstadmission exclusion_yearfilter
## Min. :0 Min. :0.0000 Min. :0.00000
## 1st Qu.:0 1st Qu.:0.0000 1st Qu.:0.00000
## Median :0 Median :0.0000 Median :0.00000
## Mean :0 Mean :0.3363 Mean :0.07171
## 3rd Qu.:0 3rd Qu.:1.0000 3rd Qu.:0.00000
## Max. :0 Max. :1.0000 Max. :1.00000
##
## exclusion_apacheiva exclusion_vitalobservations exclusion_labobservations
## Min. :0.0000 Min. :0.00000 Min. :0.00000
## 1st Qu.:0.0000 1st Qu.:0.00000 1st Qu.:0.00000
## Median :1.0000 Median :0.00000 Median :0.00000
## Mean :0.6921 Mean :0.04839 Mean :0.03725
## 3rd Qu.:1.0000 3rd Qu.:0.00000 3rd Qu.:0.00000
## Max. :1.0000 Max. :1.00000 Max. :1.00000
##
## exclusion_medobservations icu_type hasDiagnosisCodes
## Min. :0.0000 Med-Surg ICU :5712 Mode :logical
## 1st Qu.:1.0000 Mobile ICU : 33 FALSE:3625
## Median :1.0000 Burn-Trauma ICU : 0 TRUE :2120
## Mean :0.8019 Cardiac ICU : 0
## 3rd Qu.:1.0000 Cardiovascular ICU: 0
## Max. :1.0000 CCU-CTICU : 0
## (Other) : 0summary(ssd$c_sbp_min, useNA = "ifany")## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.00 75.00 92.00 92.01 109.00 347.00 198922summary(ssd_incl$c_sbp_min, useNA = "ifany")## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.00 78.00 92.00 92.14 107.00 256.00 184summary(ssd$c_mbp_min, useNA = "ifany")## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.13 56.00 66.00 70.12 78.00 359.00 250116summary(ssd_incl$c_mbp_min, useNA = "ifany")## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.13 54.00 64.00 66.76 75.00 287.00summary(ssd$c_temp_max, useNA = "ifany")## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.1 36.8 37.1 37.3 37.6 112.6 319848summary(ssd_incl$c_temp_max, useNA = "ifany")## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.10 36.90 37.17 37.32 37.60 111.20 17387summary(ssd$c_temp_min, useNA = "ifany")## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.1 36.1 36.4 36.4 36.7 108.3 319848summary(ssd_incl$c_temp_min, useNA = "ifany")## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.10 36.10 36.40 36.29 36.70 101.00 17387summary(ssd$c_resp_max, useNA = "ifany")## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.00 21.00 25.00 26.98 30.00 200.00 134725summary(ssd_incl$c_resp_max, useNA = "ifany")## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.00 22.00 26.00 28.01 31.00 199.00summary(ssd$c_HR_max, useNA = "ifany")## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.0 86.0 99.0 101.4 115.0 387.0 112042summary(ssd_incl$c_HR_max, useNA = "ifany")## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 5.0 87.0 101.0 102.9 116.0 379.014 Table 1 Exclusion versus Inclusion
Demographic, Severity of Illness, Diagnostic, and Mortality Outcome Data
varsTable1compare <- c("age", "gender2", "ethnicity2", "BMI_Ranges", "icu_admit_source2","physicianSpeciality2", "hospitaldischargeyear", "hospital_teaching_status", "hospital_size", "hospital_region2","dialysis", "aids", "hepaticfailure", "diabetes", "immunosuppression", "leukemia", "lymphoma", "metastaticcancer", "thrombolytics", "sofa_respiration_baseline2", "cardiovascular_baseline","SIRS_Positive", "qSOFA_Positive", "SOFA_Positive", "SepsisFuzzyLogicPositive","apacheiva", "hospital_mortality_ultimate", "icu_mortality", "hospital_los", "icu_los", "sepsis_outcome", "group")
library(tableone); library(survival); library(dplyr); library(Hmisc); library(ggplot2); library(sjPlot)
if(!("tableone" %in% rownames(installed.packages()))) {
install.packages("tableone")
}
Table1IncludeExclude <- CreateTableOne(data=ssd ,vars=varsTable1compare,strata="inclusiongroup",test=TRUE, includeNA=TRUE
) %>% print(nonnormal= c("icu_mortality","hospital_mortality_ultimate", "sepsis_outcome", "hospital_teaching_status"),minMax=TRUE,
printToggle = FALSE,
showAllLevels = TRUE,
cramVars = "kon"
) %>%
{data.frame(
variable_name = gsub(" ", " ", rownames(.), fixed = TRUE), .,
row.names = NULL,
check.names = FALSE,
stringsAsFactors = FALSE)} %>%
knitr::kable(caption="Exclusion versus Inclusion Demographic, Severity of Illness, Diagnostic, and Outcome Data")15 Checking hospital and regional level inclusion/exclusion
Review changes to hospital IDs due to inclusion/exclusion criteria. Hospital ID is the unique name of a hospital within the dataset. This analysis will review how many hospitals are dropped form the analyses. Hospitals that did not build interfaces between hospital information systems and the eCareManager system will be at highest risk of having patients excluded from this study. Review of regional data (included in Demographic, Severity of Illness, Diagnostic Tables) will allow readers to visualize if populations within certain region are under-represented.
ssd %>% mutate(inStudy = exclusion_yearfilter==0 & exclusion_over18==0 & exclusion_firstadmission==0 & exclusion_apacheiva==0 & exclusion_vitalobservations==0 & exclusion_labobservations==0 & exclusion_medobservations==0) %>% group_by(hospitalid) %>% summarise(n=n(),n_study=sum(inStudy),propInstudy=n_study/n)## # A tibble: 334 x 4
## hospitalid n n_study propInstudy
## <int> <int> <int> <dbl>
## 1 1 6840 0 0.
## 2 3 1702 0 0.
## 3 4 9705 0 0.
## 4 5 722 0 0.
## 5 6 1768 0 0.
## 6 7 1164 0 0.
## 7 8 5523 0 0.
## 8 9 6087 0 0.
## 9 12 3538 0 0.
## 10 13 566 0 0.
## # ... with 324 more rowsssd %>% mutate(inStudy = exclusion_yearfilter==0 & exclusion_over18==0 & exclusion_firstadmission==0 & exclusion_apacheiva==0 & exclusion_vitalobservations==0 & exclusion_labobservations==0 & exclusion_medobservations==0) %>% group_by(hospitalid) %>% summarise(n=n(),n_study=sum(inStudy),propInstudy=n_study/n) %>% ggplot(aes(propInstudy)) + geom_histogram()## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
boxplot(ssd$hospitalid,ssd_incl$hospitalid,las=2,main= "Hospital IDs Before/After Inclusion/Exclusion", names = c("Before", "After"))
ssd$albumin_apache[ssd$albumin_apache==(-1)] <- NA
ssd_incl$albumin_apache[ssd_incl$albumin_apache==(-1)] <- NA16 Descriptive
Describing variables before and after inclusion/exclusion
describe(ssd)## Warning in w * sort(x - mean(x)): longer object length is not a multiple of
## shorter object length## ssd
##
## 296 Variables 2842521 Observations
## ---------------------------------------------------------------------------
## patientunitstayid
## n missing distinct Info Mean Gmd .05 .10
## 2842521 0 2842521 1 1647239 1169471 142267 288023
## .25 .50 .75 .90 .95
## 761960 1597616 2628874 3063221 3211145
##
## lowest : 1 2 3 4 5
## highest: 3353267 3353268 3353269 3353270 3353271
## ---------------------------------------------------------------------------
## exclusion_over18
## n missing distinct Info Sum Mean Gmd
## 2842521 0 2 0.013 12202 0.004293 0.008548
##
## ---------------------------------------------------------------------------
## exclusion_firstadmission
## n missing distinct Info Sum Mean Gmd
## 2842521 0 2 0.416 472839 0.1663 0.2773
##
## ---------------------------------------------------------------------------
## exclusion_yearfilter
## n missing distinct Info Sum Mean Gmd
## 2842521 0 2 0.617 822032 0.2892 0.4111
##
## ---------------------------------------------------------------------------
## exclusion_apacheiva
## n missing distinct Info Sum Mean Gmd
## 2842521 0 2 0.705 1074507 0.378 0.4702
##
## ---------------------------------------------------------------------------
## exclusion_vitalobservations
## n missing distinct Info Sum Mean Gmd
## 2842521 0 2 0.276 291725 0.1026 0.1842
##
## ---------------------------------------------------------------------------
## exclusion_labobservations
## n missing distinct Info Sum Mean Gmd
## 2842521 0 2 0.077 74972 0.02638 0.05136
##
## ---------------------------------------------------------------------------
## exclusion_medobservations
## n missing distinct Info Sum Mean Gmd
## 2842521 0 2 0.384 428700 0.1508 0.2561
##
## ---------------------------------------------------------------------------
## hospitalid
## n missing distinct Info Mean Gmd .05 .10
## 2842521 0 334 1 257.3 138.9 56 92
## .25 .50 .75 .90 .95
## 167 256 365 420 445
##
## lowest : 1 3 4 5 6, highest: 455 456 457 458 459
## ---------------------------------------------------------------------------
## gender
## n missing distinct
## 2842521 0 5
##
## Value Female Male Other Unknown
## Frequency 4896 1309647 1527370 52 556
## Proportion 0.002 0.461 0.537 0.000 0.000
## ---------------------------------------------------------------------------
## age
## n missing distinct Info Mean Gmd .05 .10
## 2840460 2061 91 1 62.72 19.61 28 38
## .25 .50 .75 .90 .95
## 52 65 76 84 88
##
## lowest : 0 1 2 3 4, highest: 86 87 88 89 90
## ---------------------------------------------------------------------------
## ethnicity
## n missing distinct
## 2842521 0 7
##
## (47920, 0.017), African American (304105, 0.107), Asian (45050, 0.016),
## Caucasian (2152704, 0.757), Hispanic (145350, 0.051), Native American
## (25711, 0.009), Other/Unknown (121681, 0.043)
## ---------------------------------------------------------------------------
## hospital_los
## n missing distinct Info Mean Gmd .05 .10
## 2842521 0 78285 1 8.941 9.314 0.9611 1.5028
## .25 .50 .75 .90 .95
## 2.9292 5.7250 10.4799 18.6438 26.2097
##
## lowest : -6378.811 -6035.253 -4959.294 -4854.218 -4658.864
## highest: 31048.731 31504.512 36525.365 36527.378 36530.324
## ---------------------------------------------------------------------------
## hospital_size
## n missing distinct
## 2842521 0 5
##
## Value <100 100-249 250-500 >500
## Frequency 643295 141919 533513 481826 1041968
## Proportion 0.226 0.050 0.188 0.170 0.367
## ---------------------------------------------------------------------------
## hospital_teaching_status
## n missing distinct
## 2842521 0 3
##
## Value f t
## Frequency 554798 1677818 609905
## Proportion 0.195 0.590 0.215
## ---------------------------------------------------------------------------
## hospital_region
## n missing distinct
## 2842521 0 5
##
## Value Midwest Northeast South West
## Frequency 632962 753120 165767 714254 576418
## Proportion 0.223 0.265 0.058 0.251 0.203
## ---------------------------------------------------------------------------
## hospital_discharge_disposition
## n missing distinct
## 2842521 0 8
##
## Value Death Home NursingHome
## Frequency 39536 264032 1697524 147773
## Proportion 0.014 0.093 0.597 0.052
##
## Value Other OtherExternal OtherHospital SNF
## Frequency 136520 121664 115279 320193
## Proportion 0.048 0.043 0.041 0.113
## ---------------------------------------------------------------------------
## hospital_mortality
## n missing distinct
## 2807000 35521 2
##
## Value 0 1
## Frequency 2542968 264032
## Proportion 0.906 0.094
## ---------------------------------------------------------------------------
## hospital_mortality_ultimate
## n missing distinct
## 2437440 405081 2
##
## Value 0 1
## Frequency 2200750 236690
## Proportion 0.903 0.097
## ---------------------------------------------------------------------------
## hospitaladmityear
## n missing distinct Info Mean Gmd .05 .10
## 2842521 0 26 0.988 2012 3.238 2006 2007
## .25 .50 .75 .90 .95
## 2010 2012 2014 2015 2015
##
## lowest : 1913 1914 1917 1927 1929, highest: 2012 2013 2014 2015 2016
## ---------------------------------------------------------------------------
## hospitaldischargeyear
## n missing distinct
## 2842521 0 6
##
## Value -2010 2011 2012 2013 2014 2015-16
## Frequency 956304 292683 341972 357883 378924 514755
## Proportion 0.336 0.103 0.120 0.126 0.133 0.181
## ---------------------------------------------------------------------------
## icu_los
## n missing distinct Info Mean Gmd .05 .10
## 2842521 0 46709 1 2.786 3.133 0.1139 0.3146
## .25 .50 .75 .90 .95
## 0.8278 1.6104 3.0500 6.0618 9.4861
##
## lowest : -5.338194e+00 -1.097222e-01 0.000000e+00 6.944444e-04 1.388889e-03
## highest: 4.714410e+02 5.063722e+02 6.087215e+02 6.360187e+02 8.242104e+02
## ---------------------------------------------------------------------------
## icu_type
## n missing distinct
## 2842521 0 18
##
## Burn-Trauma ICU (3439, 0.001), Cardiac ICU (192048, 0.068), Cardiovascular
## ICU (12612, 0.004), CCU-CTICU (227460, 0.080), CSICU (131347, 0.046),
## CTICU (78720, 0.028), Documentation Only ICU (749, 0.000), ED ICU (27874,
## 0.010), Floating (Universal) License ICU (9064, 0.003), Med-Surg ICU
## (1527054, 0.537), MICU (248339, 0.087), Mobile ICU (5317, 0.002), Neuro
## ICU (164626, 0.058), PACU ICU (356, 0.000), SICU (179514, 0.063), Trauma
## ICU (33384, 0.012), Vent ICU (528, 0.000), Virtual ICU (90, 0.000)
## ---------------------------------------------------------------------------
## icu_admit_source
## n missing distinct
## 2842521 0 17
##
## (67402, 0.024), Acute Care/Floor (27695, 0.010), Chest Pain Center (9943,
## 0.003), Direct Admit (175631, 0.062), Emergency Department (1245659,
## 0.438), Emergency Room (149, 0.000), Floor (407519, 0.143), ICU (31038,
## 0.011), ICU to SDU (188944, 0.066), Observation (118, 0.000), Operating
## Room (367328, 0.129), Other (65, 0.000), Other Hospital (65765, 0.023),
## Other ICU (85071, 0.030), PACU (8412, 0.003), Recovery Room (109083,
## 0.038), Step-Down Unit (SDU) (52699, 0.019)
## ---------------------------------------------------------------------------
## icu_disch_location
## n missing distinct
## 2842521 0 18
##
## (4634, 0.002), Acute Care/Floor (104668, 0.037), Death (154009, 0.054),
## Floor (1587711, 0.559), Home (250587, 0.088), ICU (7465, 0.003), Nursing
## Home (3816, 0.001), Operating Room (57, 0.000), Other (25818, 0.009),
## Other External (34327, 0.012), Other Hospital (58896, 0.021), Other ICU
## (129053, 0.045), Other ICU (CABG) (974, 0.000), Other Internal (5667,
## 0.002), Rehabilitation (10269, 0.004), Skilled Nursing Facility (20506,
## 0.007), Step-Down Unit (SDU) (291173, 0.102), Telemetry (152891, 0.054)
## ---------------------------------------------------------------------------
## icu_mortality
## n missing distinct
## 2841877 644 2
##
## Value 0 1
## Frequency 2687868 154009
## Proportion 0.946 0.054
## ---------------------------------------------------------------------------
## admitsource
## n missing distinct Info Mean Gmd
## 2437440 405081 9 0.864 5.64 2.982
##
## Value -1 1 2 3 4 5 6 7
## Frequency 56303 348455 104383 9730 448939 12995 63931 169146
## Proportion 0.023 0.143 0.043 0.004 0.184 0.005 0.026 0.069
##
## Value 8
## Frequency 1223558
## Proportion 0.502
## ---------------------------------------------------------------------------
## dischargelocation
## n missing distinct Info Mean Gmd
## 2437440 405081 7 0.666 5.119 1.675
##
## Value -1 4 5 6 7 8 9
## Frequency 3755 1685490 25106 55304 208084 312857 146844
## Proportion 0.002 0.692 0.010 0.023 0.085 0.128 0.060
## ---------------------------------------------------------------------------
## bedcount
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 85 0.999 26.05 15.82 10 12
## .25 .50 .75 .90 .95
## 16 22 31 48 60
##
## lowest : 1 2 3 4 5, highest: 142 144 168 213 252
## ---------------------------------------------------------------------------
## readmit
## n missing distinct Info Sum Mean Gmd
## 2437440 405081 2 0.169 145671 0.05976 0.1124
##
## ---------------------------------------------------------------------------
## apacheiva
## n missing distinct Info Mean Gmd .05 .10
## 1831815 1010706 219 1 52.76 29.43 16 24
## .25 .50 .75 .90 .95
## 35 49 67 88 103
##
## lowest : -1 0 1 2 3, highest: 214 215 216 218 230
## ---------------------------------------------------------------------------
## apacheadmissiondx
## n missing distinct
## 2521180 321341 416
##
## lowest : Abdomen/extremity trauma Abdomen/face trauma Abdomen/multiple trauma Abdomen only trauma Abdomen/pelvis trauma
## highest: Vena cava filter insertion Ventricular Septal Defect (VSD) Repair Ventriculostomy Weaning from mechanical ventilation (transfer from other unit or hospital only) Whipple-surgery for pancreatic cancer
## ---------------------------------------------------------------------------
## dialysis
## n missing distinct
## 2437440 405081 2
##
## Value 0 1
## Frequency 2349031 88409
## Proportion 0.964 0.036
## ---------------------------------------------------------------------------
## aids
## n missing distinct
## 2437440 405081 2
##
## Value 0 1
## Frequency 2434536 2904
## Proportion 0.999 0.001
## ---------------------------------------------------------------------------
## hepaticfailure
## n missing distinct
## 2437440 405081 2
##
## Value FALSE TRUE
## Frequency 2387412 50028
## Proportion 0.979 0.021
## ---------------------------------------------------------------------------
## cirrhosis
## n missing distinct Info Sum Mean Gmd
## 2437440 405081 2 0.041 34067 0.01398 0.02756
##
## ---------------------------------------------------------------------------
## diabetes
## n missing distinct
## 2437440 405081 2
##
## Value 0 1
## Frequency 1915776 521664
## Proportion 0.786 0.214
## ---------------------------------------------------------------------------
## immunosuppression
## n missing distinct
## 2437440 405081 2
##
## Value 0 1
## Frequency 2382595 54845
## Proportion 0.977 0.023
## ---------------------------------------------------------------------------
## leukemia
## n missing distinct
## 2437440 405081 2
##
## Value 0 1
## Frequency 2420503 16937
## Proportion 0.993 0.007
## ---------------------------------------------------------------------------
## lymphoma
## n missing distinct
## 2437440 405081 2
##
## Value 0 1
## Frequency 2427829 9611
## Proportion 0.996 0.004
## ---------------------------------------------------------------------------
## metastaticcancer
## n missing distinct
## 2437440 405081 2
##
## Value 0 1
## Frequency 2391741 45699
## Proportion 0.981 0.019
## ---------------------------------------------------------------------------
## thrombolytics
## n missing distinct
## 2437440 405081 2
##
## Value 0 1
## Frequency 2396625 40815
## Proportion 0.983 0.017
## ---------------------------------------------------------------------------
## admissionheight
## n missing distinct Info Mean Gmd .05 .10
## 2699580 142941 2319 0.999 169.2 13.58 152.4 154.9
## .25 .50 .75 .90 .95
## 162.5 170.0 177.8 183.0 187.0
##
## lowest : 0.00 0.09 0.10 0.12 0.18, highest: 712.20 712.70 715.20 717.50 720.00
## ---------------------------------------------------------------------------
## admissionweight
## n missing distinct Info Mean Gmd .05 .10
## 2509427 333094 10426 1 83.26 27.57 49.9 55.0
## .25 .50 .75 .90 .95
## 65.8 79.4 95.8 114.7 129.4
##
## lowest : 0.00 0.04 0.09 0.10 0.11, highest: 983.50 987.30 992.50 993.70 993.80
## ---------------------------------------------------------------------------
## chartedweight
## n missing distinct Info Mean Gmd .05 .10
## 1347603 1494918 14441 1 83.7 27.58 49.50 55.29
## .25 .50 .75 .90 .95
## 66.10 80.01 96.80 115.48 129.86
##
## lowest : 30.00000 30.02779 30.03000 30.04140 30.06408
## highest: 299.18928 299.37072 299.50680 299.90000 300.00000
## ---------------------------------------------------------------------------
## eyes
## n missing distinct Info Mean Gmd
## 2437440 405081 5 0.66 3.28 1.147
##
## Value -1 1 2 3 4
## Frequency 130579 195272 102349 312300 1696940
## Proportion 0.054 0.080 0.042 0.128 0.696
## ---------------------------------------------------------------------------
## motor
## n missing distinct Info Mean Gmd
## 2437440 405081 7 0.566 5.148 1.444
##
## Value -1 1 2 3 4 5 6
## Frequency 130579 130349 9933 15594 117089 190116 1843780
## Proportion 0.054 0.053 0.004 0.006 0.048 0.078 0.756
## ---------------------------------------------------------------------------
## verbal
## n missing distinct Info Mean Gmd
## 2437440 405081 6 0.753 3.798 1.762
##
## Value -1 1 2 3 4 5
## Frequency 130579 396210 52559 62431 279130 1516531
## Proportion 0.054 0.163 0.022 0.026 0.115 0.622
## ---------------------------------------------------------------------------
## gcs
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 14 0.807 12.23 4.297 -3 3
## .25 .50 .75 .90 .95
## 11 15 15 15 15
##
## Value -3 3 4 5 6 7 8 9
## Frequency 130579 116582 11175 11828 44512 54124 48652 53429
## Proportion 0.054 0.048 0.005 0.005 0.018 0.022 0.020 0.022
##
## Value 10 11 12 13 14 15
## Frequency 72618 68388 57551 105293 257068 1405641
## Proportion 0.030 0.028 0.024 0.043 0.105 0.577
## ---------------------------------------------------------------------------
## unablegcs
## n missing distinct Info Mean Gmd
## 2437440 405081 3 0.152 -0.01734 0.104
##
## Value -1 0 1
## Frequency 86425 2306861 44154
## Proportion 0.035 0.946 0.018
## ---------------------------------------------------------------------------
## urine
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 85117 0.877 965.4 1383 -1 -1
## .25 .50 .75 .90 .95
## -1 0 1519 2818 3780
##
## Value 0 200000 400000 600000 800000 1000000 3200000
## Frequency 2437411 14 6 2 2 2 1
## Proportion 1 0 0 0 0 0 0
##
## Value 7200000 21600000
## Frequency 1 1
## Proportion 0 0
## ---------------------------------------------------------------------------
## pao2_apache
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 4882 0.542 29.52 51.53 -1 -1
## .25 .50 .75 .90 .95
## -1 -1 -1 112 167
##
## lowest : -1.00 1.44 1.80 2.00 2.80, highest: 694.90 715.00 757.00 774.00 840.00
## ---------------------------------------------------------------------------
## fio2_apache
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 231 0.542 12.84 22.88 -1 -1
## .25 .50 .75 .90 .95
## -1 -1 -1 50 100
##
## lowest : -1.0 21.0 21.1 22.0 22.5, highest: 99.6 99.7 99.8 99.9 100.0
## ---------------------------------------------------------------------------
## pao2fio2_apache
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 19815 0.542 54.91 93.48 -1.0 -1.0
## .25 .50 .75 .90 .95
## -1.0 -1.0 -1.0 247.2 338.1
##
## lowest : -1.000 2.880 3.300 4.500 5.000
## highest: 2704.762 2719.048 2733.333 2804.762 2847.619
## ---------------------------------------------------------------------------
## temperature_apache
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 587 0.996 32.6 7.581 -1.0 -1.0
## .25 .50 .75 .90 .95
## 36.0 36.4 36.7 37.1 37.4
##
## lowest : -1.00 20.00 20.10 20.20 20.30, highest: 42.70 42.77 42.80 42.90 43.00
## ---------------------------------------------------------------------------
## respiratoryrate_apache
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 172 0.999 23.27 17.05 4 6
## .25 .50 .75 .90 .95
## 10 25 34 43 51
##
## lowest : -1.0 4.0 4.5 5.0 5.8, highest: 57.6 58.0 59.0 59.1 60.0
## ---------------------------------------------------------------------------
## heartrate_apache
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 203 1 97.11 37.35 44 52
## .25 .50 .75 .90 .95
## 70 102 119 135 145
##
## lowest : -1 20 21 22 23, highest: 216 217 218 219 220
## ---------------------------------------------------------------------------
## mbp_apache
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 519 1 82.31 46.77 40 43
## .25 .50 .75 .90 .95
## 52 64 120 144 161
##
## lowest : -1.00 40.00 40.30 40.33 41.00, highest: 196.00 197.00 198.00 199.00 200.00
## ---------------------------------------------------------------------------
## albumin_apache
## n missing distinct Info Mean Gmd .05 .10
## 944241 1898280 101 0.998 2.863 0.8002 1.7 1.9
## .25 .50 .75 .90 .95
## 2.4 2.9 3.4 3.8 4.0
##
## lowest : 1.00 1.07 1.10 1.20 1.30, highest: 7.40 7.50 7.70 8.20 8.60
## ---------------------------------------------------------------------------
## bilirubin_apache
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 1175 0.725 -0.2343 1.151 -1.0 -1.0
## .25 .50 .75 .90 .95
## -1.0 -1.0 0.5 1.0 1.6
##
## lowest : -1.00 0.04 0.05 0.07 0.08, highest: 61.20 61.50 63.10 64.00 72.40
## ---------------------------------------------------------------------------
## bun_apache
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 1068 0.987 20.23 22.21 -1 -1
## .25 .50 .75 .90 .95
## 6 15 27 48 65
##
## lowest : -1.00 1.00 1.40 1.41 1.50, highest: 251.00 252.00 253.00 254.00 255.00
## ---------------------------------------------------------------------------
## creatinine_apache
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 2708 0.988 0.9751 1.68 -1.00 -1.00
## .25 .50 .75 .90 .95
## 0.45 0.82 1.35 2.50 4.04
##
## lowest : -1.00 0.10 0.11 0.12 0.13, highest: 24.91 24.94 24.95 24.97 25.00
## ---------------------------------------------------------------------------
## glucose_apache
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 1627 0.997 142.3 113.4 -1 -1
## .25 .50 .75 .90 .95
## 85 118 191 271 337
##
## lowest : -1.0 1.0 1.1 1.3 1.5, highest: 2796.0 2810.0 2871.0 2890.0 2954.0
## ---------------------------------------------------------------------------
## hematocrit_apache
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 654 0.987 24.79 16.56 -1.0 -1.0
## .25 .50 .75 .90 .95
## 19.6 29.9 35.9 40.2 42.6
##
## lowest : -1.0 5.0 5.1 5.2 5.3, highest: 78.0 79.8 80.0 86.0 93.0
## ---------------------------------------------------------------------------
## sodium_apache
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 295 0.987 107 51.2 -1 -1
## .25 .50 .75 .90 .95
## 128 136 140 142 145
##
## lowest : -1.0 82.0 83.0 86.0 87.0, highest: 195.0 195.7 196.0 198.0 199.0
## ---------------------------------------------------------------------------
## paco2_apache
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 1277 0.542 8.904 15.97 -1.0 -1.0
## .25 .50 .75 .90 .95
## -1.0 -1.0 -1.0 41.4 48.0
##
## lowest : -1.0 2.5 3.1 3.4 3.7, highest: 148.8 149.0 149.3 149.6 150.0
## ---------------------------------------------------------------------------
## ph_apache
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 1067 0.542 0.918 2.962 -1.000 -1.000
## .25 .50 .75 .90 .95
## -1.000 -1.000 -1.000 7.386 7.434
##
## -1 (1878455, 0.771), 6.3 (1, 0.000), 6.4 (1, 0.000), 6.5 (6, 0.000), 6.6
## (38, 0.000), 6.7 (116, 0.000), 6.8 (525, 0.000), 6.9 (1644, 0.001), 7
## (4136, 0.002), 7.1 (11523, 0.005), 7.2 (39474, 0.016), 7.3 (153742,
## 0.063), 7.4 (249333, 0.102), 7.5 (87884, 0.036), 7.6 (9721, 0.004), 7.7
## (780, 0.000), 7.8 (47, 0.000), 7.9 (11, 0.000), 8 (2, 0.000), 8.6 (1,
## 0.000)
## ---------------------------------------------------------------------------
## intubated_apache
## n missing distinct Info Sum Mean Gmd
## 2437440 405081 2 0.364 344877 0.1415 0.2429
##
## ---------------------------------------------------------------------------
## wbc_apache
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 6658 0.982 8.726 9.086 -1.0 -1.0
## .25 .50 .75 .90 .95
## -1.0 8.2 13.2 18.7 23.0
##
## lowest : -1.00 0.01 0.02 0.03 0.04, highest: 198.10 199.00 199.20 199.40 199.69
## ---------------------------------------------------------------------------
## oobintubday1_apache
## n missing distinct Info Sum Mean Gmd
## 2437440 405081 2 0.542 576561 0.2365 0.3612
##
## ---------------------------------------------------------------------------
## oobventday1_apache
## n missing distinct Info Sum Mean Gmd
## 2437440 405081 2 0.625 720884 0.2958 0.4166
##
## ---------------------------------------------------------------------------
## ventday1_apache
## n missing distinct Info Sum Mean Gmd
## 2437440 405081 2 0.511 530378 0.2176 0.3405
##
## ---------------------------------------------------------------------------
## physicianspeciality
## n missing distinct
## 2842521 0 51
##
## lowest : allergy/immunology anesthesiology anesthesiology/CCM cardiology
## highest: surgery-transplant surgery-trauma surgery-vascular unknown urology
## ---------------------------------------------------------------------------
## acutephysiologyscore
## n missing distinct Info Mean Gmd .05 .10
## 1831815 1010706 202 1 41.44 26.09 11 17
## .25 .50 .75 .90 .95
## 25 37 53 74 89
##
## lowest : -1 0 1 2 3, highest: 196 197 198 200 206
## ---------------------------------------------------------------------------
## apachescore
## n missing distinct Info Mean Gmd .05 .10
## 1831815 1010706 219 1 52.76 29.43 16 24
## .25 .50 .75 .90 .95
## 35 49 67 88 103
##
## lowest : -1 0 1 2 3, highest: 214 215 216 218 230
## ---------------------------------------------------------------------------
## predictedicumortality
## n missing distinct Info Mean Gmd
## 1831815 1010706 1692781 1 -0.0002665 0.2211
## .05 .10 .25 .50 .75 .90
## -1.000000 0.002384 0.007386 0.020175 0.058554 0.173918
## .95
## 0.331791
##
## lowest : -1.000000e+00 2.798800e-10 5.105833e-10 5.425713e-10 5.718087e-10
## highest: 9.833071e-01 9.851197e-01 9.859533e-01 9.912570e-01 9.951461e-01
## ---------------------------------------------------------------------------
## predictediculos
## n missing distinct Info Mean Gmd .05 .10
## 1831815 1010706 1691249 1 3.59 2.705 -1.000 1.153
## .25 .50 .75 .90 .95
## 2.019 3.186 5.023 7.085 8.167
##
## lowest : -1.0000000000 0.0002397692 0.0005581499 0.0010462120 0.0015511424
## highest: 16.0262378684 16.4066825345 18.7383148958 19.8923078627 19.9075117024
## ---------------------------------------------------------------------------
## predictedhospitalmortality
## n missing distinct Info Mean Gmd .05 .10
## 1831815 1010706 1608618 0.999 -0.01157 0.3362 -1.00000 -1.00000
## .25 .50 .75 .90 .95
## 0.01404 0.04111 0.11272 0.27991 0.46046
##
## lowest : -1.0000000000 0.0002555227 0.0003451466 0.0003794773 0.0003825366
## highest: 0.9963869130 0.9979823377 0.9981384119 0.9993184841 0.9998248676
## ---------------------------------------------------------------------------
## predictedhospitallos
## n missing distinct Info Mean Gmd .05 .10
## 1831815 1010706 1608464 0.999 8.937 6.254 -1.000 -1.000
## .25 .50 .75 .90 .95
## 5.815 8.822 12.041 15.587 18.469
##
## lowest : -1.000000e+00 5.815364e-05 9.883428e-04 3.367056e-03 4.531164e-03
## highest: 1.288372e+02 1.331938e+02 1.469374e+02 2.234267e+02 2.249389e+02
## ---------------------------------------------------------------------------
## preopmi
## n missing distinct Info Sum Mean Gmd
## 1831815 1010706 2 0.01 6124 0.003343 0.006664
##
## ---------------------------------------------------------------------------
## preopcardiaccath
## n missing distinct Info Sum Mean Gmd
## 1831815 1010706 2 0.028 17018 0.00929 0.01841
##
## ---------------------------------------------------------------------------
## ptcawithin24h
## n missing distinct Info Sum Mean Gmd
## 1831815 1010706 2 0.177 115287 0.06294 0.118
##
## ---------------------------------------------------------------------------
## graftcount
## n missing distinct Info Mean Gmd .05 .10
## 2437440 405081 10 0.044 3 0.04009 3 3
## .25 .50 .75 .90 .95
## 3 3 3 3 3
##
## Value 1 2 3 4 5 6 7 8
## Frequency 6600 11407 2400785 13860 3894 724 128 31
## Proportion 0.003 0.005 0.985 0.006 0.002 0.000 0.000 0.000
##
## Value 9 10
## Frequency 7 4
## Proportion 0.000 0.000
## ---------------------------------------------------------------------------
## mbp_min
## n missing distinct Info Mean Gmd .05 .10
## 2487252 355269 239 1 58.47 19.49 28 37
## .25 .50 .75 .90 .95
## 48 59 70 80 86
##
## lowest : 1 2 3 4 5, highest: 330 342 345 353 360
## ---------------------------------------------------------------------------
## sbp_min
## n missing distinct Info Mean Gmd .05 .10
## 2487021 355500 223 1 60.42 19.64 30 38
## .25 .50 .75 .90 .95
## 50 60 71 82 89
##
## lowest : 1 2 3 4 5, highest: 290 294 302 313 347
## ---------------------------------------------------------------------------
## temperature_min
## n missing distinct Info Mean Gmd .05 .10
## 215636 2626885 2261 1 40.03 12.86 25.00 31.44
## .25 .50 .75 .90 .95
## 35.00 36.10 36.90 38.20 96.80
##
## lowest : 0.05 0.10 0.15 0.20 0.25, highest: 116.00 117.00 122.00 131.00 137.00
## ---------------------------------------------------------------------------
## temperature_max
## n missing distinct Info Mean Gmd .05 .10
## 215636 2626885 1238 0.999 43.52 11.59 36.2 36.8
## .25 .50 .75 .90 .95
## 37.3 37.8 38.5 40.7 100.0
##
## lowest : 0.1 0.4 1.1 1.5 1.9, highest: 157.0 168.0 173.0 176.0 224.5
## ---------------------------------------------------------------------------
## heartrate_max
## n missing distinct Info Mean Gmd .05 .10
## 2533730 308791 295 1 106.9 24.84 74 80
## .25 .50 .75 .90 .95
## 91 105 120 136 146
##
## lowest : 5 6 7 8 9, highest: 296 297 298 299 300
## ---------------------------------------------------------------------------
## respiratoryrate_max
## n missing distinct Info Mean Gmd .05 .10
## 2380824 461697 210 0.998 32.07 12.85 20 21
## .25 .50 .75 .90 .95
## 24 28 35 46 56
##
## Value 0 500 3000 13500 19000 27000 37000 51000
## Frequency 2380814 1 1 1 1 1 1 1
## Proportion 1 0 0 0 0 0 0 0
##
## Value 57500 58500 63000
## Frequency 1 1 1
## Proportion 0 0 0
## ---------------------------------------------------------------------------
## heartrate_charted_max
## n missing distinct Info Mean Gmd .05 .10
## 2140138 702383 314 1 100.4 24.95 68 74
## .25 .50 .75 .90 .95
## 85 98 114 130 140
##
## lowest : 1 2 3 5 6, highest: 374 379 380 383 387
## ---------------------------------------------------------------------------
## respiratoryrate_charted_max
## n missing distinct Info Mean Gmd .05 .10
## 2214083 628438 82 0.998 26.35 9.094 16 18
## .25 .50 .75 .90 .95
## 20 25 30 37 43
##
## lowest : 1 2 3 4 5, highest: 75 76 77 78 79
## ---------------------------------------------------------------------------
## o2saturation_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 1988990 853531 104 0.994 92.09 6.865 81 86
## .25 .50 .75 .90 .95
## 91 94 96 98 99
##
## lowest : 0.5 1.0 2.0 3.0 4.0, highest: 96.0 97.0 98.0 99.0 100.0
## ---------------------------------------------------------------------------
## nibp_systolic_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 2094497 748024 290 1 100.6 24.75 67 74
## .25 .50 .75 .90 .95
## 86 99 114 129 140
##
## lowest : 1 2 3 4 5, highest: 263 264 266 269 278
## ---------------------------------------------------------------------------
## nibp_diastolic_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 2095949 746572 227 1 51.67 16.42 28 34
## .25 .50 .75 .90 .95
## 42 51 60 70 77
##
## lowest : 1 2 3 4 5, highest: 208 213 216 226 235
## ---------------------------------------------------------------------------
## nibp_mean_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 2005131 837390 581 1 66.77 18.28 42 48
## .25 .50 .75 .90 .95
## 56 66 77 88 95
##
## lowest : 0.13 0.56 0.61 0.74 0.87, highest: 215.00 219.00 223.00 232.00 242.00
## ---------------------------------------------------------------------------
## ibp_systolic_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 455101 2387420 347 1 97.42 27.76 60 70
## .25 .50 .75 .90 .95
## 82 95 111 130 142
##
## lowest : 1 2 3 4 5, highest: 346 347 348 364 390
## ---------------------------------------------------------------------------
## ibp_diastolic_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 454978 2387543 297 0.999 48.81 14.45 30 34
## .25 .50 .75 .90 .95
## 41 48 56 65 72
##
## lowest : 1.0 2.0 3.0 3.4 4.0, highest: 340.0 346.0 347.0 348.0 390.0
## ---------------------------------------------------------------------------
## ibp_mean_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 482296 2360225 440 1 65.41 18.82 40 48
## .25 .50 .75 .90 .95
## 56 64 74 86 94
##
## lowest : 0.9 1.0 2.0 3.0 4.0, highest: 359.0 360.0 362.0 364.0 390.0
## ---------------------------------------------------------------------------
## mbp_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 2098791 743730 668 1 65.78 18.43 41 47
## .25 .50 .75 .90 .95
## 55 65 76 87 94
##
## lowest : 0.13 0.56 0.61 0.74 0.87, highest: 293.00 318.00 325.00 347.00 359.00
## ---------------------------------------------------------------------------
## sbp_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 2139934 702587 291 1 99.09 25.16 64 73
## .25 .50 .75 .90 .95
## 85 98 113 128 138
##
## lowest : 1 2 3 4 5, highest: 256 257 260 261 264
## ---------------------------------------------------------------------------
## temperature_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 2358568 483953 856 0.996 36.33 0.7058 35.2 35.6
## .25 .50 .75 .90 .95
## 36.1 36.4 36.7 37.0 37.2
##
## lowest : 20.10000 20.11111 20.20000 20.22000 20.30000
## highest: 43.30000 45.00000 45.30000 46.20000 48.20000
## ---------------------------------------------------------------------------
## temperature_charted_max
## n missing distinct Info Mean Gmd .05 .10
## 2358568 483953 781 0.997 37.25 0.7737 36.3 36.6
## .25 .50 .75 .90 .95
## 36.8 37.1 37.6 38.2 38.7
##
## lowest : 21.00 21.70 23.70 25.10 25.60, highest: 48.88 48.90 49.00 49.05 49.30
## ---------------------------------------------------------------------------
## gcs_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 1457027 1385494 20 0.863 12.54 3.545 3 6
## .25 .50 .75 .90 .95
## 11 15 15 15 15
##
## 3 (95412, 0.065), 4 (8918, 0.006), 4.5 (1, 0.000), 5 (8711, 0.006), 6
## (38400, 0.026), 7 (47093, 0.032), 8 (43898, 0.030), 8.5 (1, 0.000), 9
## (41618, 0.029), 9.5 (1, 0.000), 10 (64099, 0.044), 11 (51164, 0.035), 11.5
## (1, 0.000), 12 (35063, 0.024), 13 (73406, 0.050), 13.5 (1, 0.000), 14
## (204798, 0.141), 14.5 (6, 0.000), 14.6 (1, 0.000), 15 (744435, 0.511)
## ---------------------------------------------------------------------------
## bilirubin_max
## n missing distinct Info Mean Gmd .05 .10
## 1073398 1769123 1289 0.994 1.184 1.273 0.2 0.3
## .25 .50 .75 .90 .95
## 0.4 0.7 1.1 2.0 3.4
##
## lowest : 0.00 0.04 0.05 0.06 0.07, highest: 99.00 107.00 116.80 159.00 198.00
## ---------------------------------------------------------------------------
## creatinine_max
## n missing distinct Info Mean Gmd .05 .10
## 2385233 457288 3017 1 1.555 1.287 0.51 0.60
## .25 .50 .75 .90 .95
## 0.77 1.00 1.57 2.98 4.67
##
## lowest : 0.00 0.06 0.07 0.08 0.09, highest: 220.00 241.00 335.00 363.00 405.00
## ---------------------------------------------------------------------------
## lactate_min
## n missing distinct Info Mean Gmd .05 .10
## 494007 2348514 1995 0.999 2.233 1.971 0.6 0.7
## .25 .50 .75 .90 .95
## 1.0 1.5 2.3 4.1 6.4
##
## lowest : 0.00 0.05 0.06 0.08 0.10, highest: 199.50 215.76 222.20 265.49 557.00
## ---------------------------------------------------------------------------
## lactate_max
## n missing distinct Info Mean Gmd .05 .10
## 494007 2348514 2418 0.999 2.987 2.824 0.700 0.800
## .25 .50 .75 .90 .95
## 1.200 1.900 3.300 6.200 9.444
##
## lowest : 0.00 0.05 0.06 0.10 0.11, highest: 244.75 251.65 278.43 509.00 557.00
## ---------------------------------------------------------------------------
## pao2_min
## n missing distinct Info Mean Gmd .05 .10
## 927841 1914680 4444 1 102.4 57.85 45.0 54.7
## .25 .50 .75 .90 .95
## 67.0 84.0 115.0 167.0 218.0
##
## Value 0 100 200 300 400 500 600 700 800
## Frequency 66811 738900 88379 19178 9380 4364 774 40 4
## Proportion 0.072 0.796 0.095 0.021 0.010 0.005 0.001 0.000 0.000
##
## Value 900 1000 1100 1600 2200 2500 2800 5300 11800
## Frequency 2 2 1 1 1 1 1 1 1
## Proportion 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
## ---------------------------------------------------------------------------
## pao2_max
## n missing distinct Info Mean Gmd .05 .10
## 927841 1914680 5816 1 169.1 118.1 61.0 69.0
## .25 .50 .75 .90 .95
## 86.8 126.0 214.0 348.0 424.0
##
## Value 0 500 1000 1500 2000 2500 3000 3500 4000
## Frequency 745251 182506 52 5 7 3 3 1 1
## Proportion 0.803 0.197 0.000 0.000 0.000 0.000 0.000 0.000 0.000
##
## Value 4500 5500 6000 7000 10000 12000 27500 31000
## Frequency 2 3 1 2 1 1 1 1
## Proportion 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
## ---------------------------------------------------------------------------
## paco2_min
## n missing distinct Info Mean Gmd .05 .10
## 924370 1918151 1400 1 38.85 12.4 23.7 27.0
## .25 .50 .75 .90 .95
## 31.8 37.0 43.3 53.0 61.4
##
## Value -100 0 50 100 150 200 250 300 350
## Frequency 1 59355 849661 14957 329 32 5 5 1
## Proportion 0.000 0.064 0.919 0.016 0.000 0.000 0.000 0.000 0.000
##
## Value 400 450 500 550 750 3100 3650 3850 4550
## Frequency 4 9 4 2 1 1 1 1 1
## Proportion 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
## ---------------------------------------------------------------------------
## paco2_max
## n missing distinct Info Mean Gmd .05 .10
## 924370 1918151 1779 1 45.91 16.07 27.6 31.0
## .25 .50 .75 .90 .95
## 36.0 42.9 51.0 64.6 77.0
##
## lowest : 0.00 2.50 2.80 3.00 3.94
## highest: 4107.00 4560.00 6537.00 7536.00 7572.00
## ---------------------------------------------------------------------------
## platelet_min
## n missing distinct Info Mean Gmd .05 .10
## 2286920 555601 1377 1 201.2 103 69 94
## .25 .50 .75 .90 .95
## 138 189 248 317 372
##
## Value -1e+05 0e+00 1e+03 2e+03 3e+03
## Frequency 1 2259260 27597 60 2
## Proportion 0.000 0.988 0.012 0.000 0.000
## ---------------------------------------------------------------------------
## inr_max
## n missing distinct Info Mean Gmd .05 .10
## 1005835 1836686 1602 0.993 1.609 0.8039 1.0 1.0
## .25 .50 .75 .90 .95
## 1.1 1.3 1.6 2.5 3.4
##
## lowest : 0.000 0.400 0.500 0.600 0.660
## highest: 58.389 76.100 79.400 81.700 130.000
## ---------------------------------------------------------------------------
## wbc_min
## n missing distinct Info Mean Gmd .05 .10
## 2291098 551423 6766 1 11.27 6.306 4.3 5.4
## .25 .50 .75 .90 .95
## 7.3 9.9 13.5 18.1 22.0
##
## lowest : 0.00 0.01 0.02 0.03 0.04, highest: 774.00 776.40 778.40 788.90 813.90
## ---------------------------------------------------------------------------
## wbc_max
## n missing distinct Info Mean Gmd .05 .10
## 2291098 551423 7404 1 12.58 7.48 4.7 5.8
## .25 .50 .75 .90 .95
## 7.9 10.8 14.9 20.3 24.7
##
## Value 0 5000 15000 345000
## Frequency 2291094 2 1 1
## Proportion 1 0 0 0
## ---------------------------------------------------------------------------
## ptt_max
## n missing distinct Info Mean Gmd .05 .10
## 748965 2093556 3040 1 45.34 26.29 24.0 25.7
## .25 .50 .75 .90 .95
## 28.9 34.0 46.8 81.6 113.0
##
## Value -200 0 50 100 150 200 250 300 350
## Frequency 1 63341 598056 59116 20435 7027 734 241 8
## Proportion 0.000 0.085 0.799 0.079 0.027 0.009 0.001 0.000 0.000
##
## Value 400 600 700 2950
## Frequency 3 1 1 1
## Proportion 0.000 0.000 0.000 0.000
## ---------------------------------------------------------------------------
## bands_max
## n missing distinct Info Mean Gmd .05 .10
## 231838 2610683 1581 0.998 12.92 14.22 0.4 1.0
## .25 .50 .75 .90 .95
## 3.0 8.0 18.0 32.0 43.0
##
## Value 0 50 100 200 6400
## Frequency 195803 34956 1077 1 1
## Proportion 0.845 0.151 0.005 0.000 0.000
## ---------------------------------------------------------------------------
## ph_min
## n missing distinct Info Mean Gmd .05 .10
## 915917 1926604 1241 1 7.633 0.7309 7.118 7.190
## .25 .50 .75 .90 .95
## 7.280 7.350 7.409 7.453 7.480
##
## Value 0 1000 7000 70000 71000
## Frequency 915892 15 7 2 1
## Proportion 1 0 0 0 0
## ---------------------------------------------------------------------------
## basedeficit_min
## n missing distinct Info Mean Gmd .05 .10
## 144509 2698012 519 0.999 6.074 5.45 0.6 1.0
## .25 .50 .75 .90 .95
## 2.4 4.8 8.0 13.0 17.0
##
## Value -30 -25 -20 -15 -10 -5 0 5 10 15
## Frequency 3 8 22 43 157 379 36963 65846 24958 9350
## Proportion 0.000 0.000 0.000 0.000 0.001 0.003 0.256 0.456 0.173 0.065
##
## Value 20 25 30 35 40 100 110 405
## Frequency 4403 1893 456 24 1 1 1 1
## Proportion 0.030 0.013 0.003 0.000 0.000 0.000 0.000 0.000
## ---------------------------------------------------------------------------
## basedeficit_max
## n missing distinct Info Mean Gmd .05 .10
## 144509 2698012 519 0.999 6.074 5.45 0.6 1.0
## .25 .50 .75 .90 .95
## 2.4 4.8 8.0 13.0 17.0
##
## Value -30 -25 -20 -15 -10 -5 0 5 10 15
## Frequency 3 8 22 43 157 379 36963 65846 24958 9350
## Proportion 0.000 0.000 0.000 0.000 0.001 0.003 0.256 0.456 0.173 0.065
##
## Value 20 25 30 35 40 100 110 405
## Frequency 4403 1893 456 24 1 1 1 1
## Proportion 0.030 0.013 0.003 0.000 0.000 0.000 0.000 0.000
## ---------------------------------------------------------------------------
## ast_max
## n missing distinct Info Mean Gmd .05 .10
## 1096980 1745541 9287 1 166.9 269.9 12 15
## .25 .50 .75 .90 .95
## 20 32 67 182 411
##
## 0 (1090745, 0.994), 10000 (5492, 0.005), 20000 (620, 0.001), 30000 (86,
## 0.000), 40000 (21, 0.000), 50000 (4, 0.000), 60000 (2, 0.000), 110000 (1,
## 0.000), 2e+05 (1, 0.000), 210000 (1, 0.000), 260000 (1, 0.000), 440000 (1,
## 0.000), 460000 (1, 0.000), 660000 (1, 0.000), 720000 (1, 0.000), 760000
## (1, 0.000), 790000 (1, 0.000)
## ---------------------------------------------------------------------------
## alt_max
## n missing distinct Info Mean Gmd .05 .10
## 1081566 1760955 6325 1 105.6 159.3 10 12
## .25 .50 .75 .90 .95
## 18 29 51 122 271
##
## Value 0 5000 10000 15000 20000 25000 30000 65000
## Frequency 1074150 6686 653 62 5 1 1 1
## Proportion 0.993 0.006 0.001 0.000 0.000 0.000 0.000 0.000
##
## Value 190000 255000 275000 305000 365000 385000 475000
## Frequency 1 1 1 1 1 1 1
## Proportion 0.000 0.000 0.000 0.000 0.000 0.000 0.000
## ---------------------------------------------------------------------------
## alp_max
## n missing distinct Info Mean Gmd .05 .10
## 1072207 1770314 1853 1 107.4 79.26 40 46
## .25 .50 .75 .90 .95
## 59 79 111 167 230
##
## Value 0 10000 20000 720000 790000 800000 830000 860000
## Frequency 1072192 7 1 1 1 1 2 1
## Proportion 1 0 0 0 0 0 0 0
##
## Value 870000
## Frequency 1
## Proportion 0
## ---------------------------------------------------------------------------
## penicilin
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.015 12184 0.005141 0.01023
##
## ---------------------------------------------------------------------------
## penicilin_anti_staph
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.004 2800 0.001181 0.00236
##
## ---------------------------------------------------------------------------
## penicilin_anti_pseudo
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.305 272294 0.1149 0.2034
##
## ---------------------------------------------------------------------------
## augmentin_unasyn
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.034 27425 0.01157 0.02287
##
## ---------------------------------------------------------------------------
## cephalosporin_1st_gen
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.108 89002 0.03755 0.07228
##
## ---------------------------------------------------------------------------
## cephalosporin_2nd_gen
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.086 69803 0.02945 0.05717
##
## ---------------------------------------------------------------------------
## cephalosporin_3rd_gen
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.199 169232 0.0714 0.1326
##
## ---------------------------------------------------------------------------
## cephalosporin_4th_5th_gen
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.082 66907 0.02823 0.05486
##
## ---------------------------------------------------------------------------
## carbapenems
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.076 61460 0.02593 0.05052
##
## ---------------------------------------------------------------------------
## monobactam
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.028 21995 0.00928 0.01839
##
## ---------------------------------------------------------------------------
## fq
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.234 201815 0.08515 0.1558
##
## ---------------------------------------------------------------------------
## vancomycin
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.402 377683 0.1593 0.2679
##
## ---------------------------------------------------------------------------
## amg
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.045 36180 0.01526 0.03006
##
## ---------------------------------------------------------------------------
## polymixins
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.002 1844 0.000778 0.001555
##
## ---------------------------------------------------------------------------
## linezolid
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.024 19052 0.008038 0.01595
##
## ---------------------------------------------------------------------------
## dapto
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.009 7331 0.003093 0.006167
##
## ---------------------------------------------------------------------------
## clinda
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.049 39628 0.01672 0.03288
##
## ---------------------------------------------------------------------------
## doxycyclin
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.021 16319 0.006885 0.01368
##
## ---------------------------------------------------------------------------
## macrolides
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.106 87141 0.03677 0.07083
##
## ---------------------------------------------------------------------------
## sulfa
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.023 18133 0.00765 0.01518
##
## ---------------------------------------------------------------------------
## metronidazole
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.122 101093 0.04265 0.08167
##
## ---------------------------------------------------------------------------
## nitrofurantoin
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.004 3376 0.001424 0.002845
##
## ---------------------------------------------------------------------------
## tigecycline
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.006 4855 0.002048 0.004088
##
## ---------------------------------------------------------------------------
## ceftriaxone
## n missing distinct Info Mean Gmd
## 2370194 472327 1 0 0 0
##
## Value 0
## Frequency 2370194
## Proportion 1
## ---------------------------------------------------------------------------
## cefotaxime
## n missing distinct Info Mean Gmd
## 2370194 472327 1 0 0 0
##
## Value 0
## Frequency 2370194
## Proportion 1
## ---------------------------------------------------------------------------
## ampicillin_sulbactam
## n missing distinct Info Mean Gmd
## 2370194 472327 1 0 0 0
##
## Value 0
## Frequency 2370194
## Proportion 1
## ---------------------------------------------------------------------------
## levofloxacin
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.047 37558 0.01585 0.03119
##
## ---------------------------------------------------------------------------
## moxifloxacin
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.004 3108 0.001311 0.002619
##
## ---------------------------------------------------------------------------
## piperacillin_tazobactam
## n missing distinct Info Mean Gmd
## 2370194 472327 1 0 0 0
##
## Value 0
## Frequency 2370194
## Proportion 1
## ---------------------------------------------------------------------------
## cefepim
## n missing distinct Info Mean Gmd
## 2370194 472327 1 0 0 0
##
## Value 0
## Frequency 2370194
## Proportion 1
## ---------------------------------------------------------------------------
## meropenem
## n missing distinct Info Mean Gmd
## 2370194 472327 1 0 0 0
##
## Value 0
## Frequency 2370194
## Proportion 1
## ---------------------------------------------------------------------------
## imipenem
## n missing distinct Info Mean Gmd
## 2370194 472327 1 0 0 0
##
## Value 0
## Frequency 2370194
## Proportion 1
## ---------------------------------------------------------------------------
## doripenem
## n missing distinct Info Mean Gmd
## 2370194 472327 1 0 0 0
##
## Value 0
## Frequency 2370194
## Proportion 1
## ---------------------------------------------------------------------------
## gentamicin
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0 47 1.983e-05 3.966e-05
##
## ---------------------------------------------------------------------------
## tobramycin
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0 349 0.0001472 0.0002944
##
## ---------------------------------------------------------------------------
## amikacin
## n missing distinct Info Mean Gmd
## 2370194 472327 1 0 0 0
##
## Value 0
## Frequency 2370194
## Proportion 1
## ---------------------------------------------------------------------------
## dopamine_infusion
## n missing distinct Info Sum Mean Gmd
## 2842521 0 2 0.06 58203 0.02048 0.04011
##
## ---------------------------------------------------------------------------
## epinephrine_infusion
## n missing distinct Info Sum Mean Gmd
## 2842521 0 2 0.024 23201 0.008162 0.01619
##
## ---------------------------------------------------------------------------
## norepinephrine_infusion
## n missing distinct Info Sum Mean Gmd
## 2842521 0 2 0.172 173100 0.0609 0.1144
##
## ---------------------------------------------------------------------------
## phenylephrine_infusion
## n missing distinct Info Sum Mean Gmd
## 2842521 0 2 0.06 58403 0.02055 0.04025
##
## ---------------------------------------------------------------------------
## vasopressin_infusion
## n missing distinct Info Sum Mean Gmd
## 836528 2005993 2 0.12 34844 0.04165 0.07984
##
## ---------------------------------------------------------------------------
## milrinone_infusion
## n missing distinct Info Sum Mean Gmd
## 2842521 0 2 0.018 16945 0.005961 0.01185
##
## ---------------------------------------------------------------------------
## heparin_infusion
## n missing distinct Info Sum Mean Gmd
## 836528 2005993 2 0.3 94183 0.1126 0.1998
##
## ---------------------------------------------------------------------------
## dopamine_medication
## n missing distinct Info Sum Mean Gmd
## 2842521 0 2 0.138 137414 0.04834 0.09201
##
## ---------------------------------------------------------------------------
## epinephrine_medication
## n missing distinct Info Sum Mean Gmd
## 2842521 0 2 0.106 104423 0.03674 0.07077
##
## ---------------------------------------------------------------------------
## norepinephrine_medication
## n missing distinct Info Sum Mean Gmd
## 2842521 0 2 0.233 241746 0.08505 0.1556
##
## ---------------------------------------------------------------------------
## phenylephrine_medication
## n missing distinct Info Sum Mean Gmd
## 2842521 0 2 0.122 120575 0.04242 0.08124
##
## ---------------------------------------------------------------------------
## vasopressin_medication
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.11 90744 0.03829 0.07364
##
## ---------------------------------------------------------------------------
## milrinone_medication
## n missing distinct Info Sum Mean Gmd
## 2842521 0 2 0.028 26753 0.009412 0.01865
##
## ---------------------------------------------------------------------------
## heparin_medication
## n missing distinct Info Sum Mean Gmd
## 2370194 472327 2 0.525 536475 0.2263 0.3502
##
## ---------------------------------------------------------------------------
## sepsis
## n missing distinct Info Sum Mean Gmd
## 2391341 451180 2 0.321 291609 0.1219 0.2141
##
## ---------------------------------------------------------------------------
## sepsis_priority
## n missing distinct Info Mean Gmd
## 2391341 451180 4 0.323 0.1929 0.3507
##
## Value 0 1 2 3
## Frequency 2099732 182938 47553 61118
## Proportion 0.878 0.077 0.020 0.026
## ---------------------------------------------------------------------------
## infection
## n missing distinct Info Sum Mean Gmd
## 2391341 451180 2 0.597 655487 0.2741 0.3979
##
## ---------------------------------------------------------------------------
## infection_priority
## n missing distinct Info Mean Gmd
## 2391341 451180 4 0.614 0.4882 0.7754
##
## Value 0 1 2 3
## Frequency 1735854 316115 166797 172575
## Proportion 0.726 0.132 0.070 0.072
## ---------------------------------------------------------------------------
## aidshiv
## n missing distinct Info Sum Mean Gmd
## 2391341 451180 2 0.011 9008 0.003767 0.007505
##
## ---------------------------------------------------------------------------
## aidshiv_priority
## n missing distinct Info Mean Gmd
## 2391341 451180 4 0.011 0.009231 0.0184
##
## Value 0 1 2 3
## Frequency 2382333 180 4590 4238
## Proportion 0.996 0.000 0.002 0.002
## ---------------------------------------------------------------------------
## organfailure
## n missing distinct Info Sum Mean Gmd
## 2391341 451180 2 0.719 954040 0.399 0.4796
##
## ---------------------------------------------------------------------------
## organfailure_priority
## n missing distinct Info Mean Gmd
## 2391341 451180 4 0.775 0.7306 1.019
##
## Value 0 1 2 3
## Frequency 1437301 418134 278763 257143
## Proportion 0.601 0.175 0.117 0.108
## ---------------------------------------------------------------------------
## altered_mental_status
## n missing distinct Info Sum Mean Gmd
## 2391341 451180 2 0.244 213500 0.08928 0.1626
##
## ---------------------------------------------------------------------------
## altered_mental_status_priority
## n missing distinct Info Mean Gmd
## 2391341 451180 4 0.245 0.195 0.3614
##
## Value 0 1 2 3
## Frequency 2177841 41341 91502 80657
## Proportion 0.911 0.017 0.038 0.034
## ---------------------------------------------------------------------------
## infection_apache
## n missing distinct Info Sum Mean Gmd
## 2437440 405081 2 0.392 377006 0.1547 0.2615
##
## ---------------------------------------------------------------------------
## organfailure_apache
## n missing distinct Info Sum Mean Gmd
## 2437440 405081 2 0.16 138153 0.05668 0.1069
##
## ---------------------------------------------------------------------------
## prompt_inflam
## n missing distinct Info Sum Mean Gmd
## 798808 2043713 2 0.493 165756 0.2075 0.3289
##
## ---------------------------------------------------------------------------
## prompt_severe_sepsis
## n missing distinct Info Sum Mean Gmd
## 798808 2043713 2 0.222 64231 0.08041 0.1479
##
## ---------------------------------------------------------------------------
## prompt_sepsis
## n missing distinct Info Sum Mean Gmd
## 798808 2043713 2 0.103 28309 0.03544 0.06837
##
## ---------------------------------------------------------------------------
## prompt_inflam_with_org_dys
## n missing distinct Info Sum Mean Gmd
## 798808 2043713 2 0.009 2323 0.002908 0.005799
##
## ---------------------------------------------------------------------------
## prompt_clinical_respone_req
## n missing distinct Info Sum Mean Gmd
## 798808 2043713 2 0.007 796984 0.9977 0.004556
##
## ---------------------------------------------------------------------------
## sofa_respiration
## n missing distinct Info Mean Gmd
## 2842521 0 5 0.32 0.2906 0.5244
##
## Value 0 1 2 3 4
## Frequency 2498811 45660 154287 103252 40511
## Proportion 0.879 0.016 0.054 0.036 0.014
## ---------------------------------------------------------------------------
## sofa_coagulation
## n missing distinct Info Mean Gmd
## 2842521 0 5 0.561 0.3582 0.5818
##
## Value 0 1 2 3 4
## Frequency 2153931 431349 197458 47111 12672
## Proportion 0.758 0.152 0.069 0.017 0.004
## ---------------------------------------------------------------------------
## sofa_liver
## n missing distinct Info Mean Gmd
## 2842521 0 5 0.238 0.1393 0.2601
##
## Value 0 1 2 3 4
## Frequency 2595771 132730 88556 15751 9713
## Proportion 0.913 0.047 0.031 0.006 0.003
## ---------------------------------------------------------------------------
## sofa_cardiovascular
## n missing distinct Info Mean Gmd
## 2842521 0 3 0.824 1 0.9772
##
## Value 0 1 3
## Frequency 915581 1469117 457823
## Proportion 0.322 0.517 0.161
## ---------------------------------------------------------------------------
## sofa_cns
## n missing distinct Info Mean Gmd
## 2842521 0 5 0.679 0.6754 1.044
##
## Value 0 1 2 3 4
## Frequency 1941301 362361 198557 200717 139585
## Proportion 0.683 0.127 0.070 0.071 0.049
## ---------------------------------------------------------------------------
## sofa_renal
## n missing distinct Info Mean Gmd
## 2842521 0 5 0.731 0.7193 1.078
##
## Value 0 1 2 3 4
## Frequency 1822342 490015 204535 156907 168722
## Proportion 0.641 0.172 0.072 0.055 0.059
## ---------------------------------------------------------------------------
## sofa_renal_baseline
## n missing distinct Info Mean Gmd
## 2842521 0 2 0.09 0.1244 0.2411
##
## Value 0 4
## Frequency 2754112 88409
## Proportion 0.969 0.031
## ---------------------------------------------------------------------------
## sofa_liver_baseline
## n missing distinct Info Mean Gmd
## 2842521 0 2 0.052 0.0704 0.1383
##
## Value 0 4
## Frequency 2792493 50028
## Proportion 0.982 0.018
## ---------------------------------------------------------------------------
## sofa_respiration_baseline
## n missing distinct Info Mean Gmd
## 2842521 0 2 0.483 0.403 0.6436
##
## Value 0 2
## Frequency 2269755 572766
## Proportion 0.799 0.201
## ---------------------------------------------------------------------------
## cardiovascular_baseline
## n missing distinct
## 2842521 0 2
##
## Value 0 1
## Frequency 2290527 551994
## Proportion 0.806 0.194
## ---------------------------------------------------------------------------
## soi_alpha
## n missing distinct Info Mean Gmd .05 .10
## 1670335 1172186 487 0.999 2.976 0.5121 2.50 2.52
## .25 .50 .75 .90 .95
## 2.60 2.83 3.14 3.67 4.00
##
## lowest : 2.50 2.51 2.52 2.53 2.54, highest: 7.83 7.85 7.88 7.94 8.00
## ---------------------------------------------------------------------------
## soi_minutes
## n missing distinct Info Mean Gmd .05 .10
## 1670335 1172186 301 0.996 196.7 316.8 -60 -60
## .25 .50 .75 .90 .95
## 0 45 265 735 990
##
## lowest : -60 -55 -50 -45 -40, highest: 1420 1425 1430 1435 1440
## ---------------------------------------------------------------------------
## od_alpha
## n missing distinct Info Mean Gmd
## 2107497 735024 7 0.328 1.156 0.2804
##
## Value 1 2 3 4 5 6 7
## Frequency 1845543 206506 44828 9213 1289 113 5
## Proportion 0.876 0.098 0.021 0.004 0.001 0.000 0.000
## ---------------------------------------------------------------------------
## od_minutes
## n missing distinct Info Mean Gmd .05 .10
## 2107497 735024 301 0.967 161.3 301.4 -60 -60
## .25 .50 .75 .90 .95
## -60 20 225 650 930
##
## lowest : -60 -55 -50 -45 -40, highest: 1420 1425 1430 1435 1440
## ---------------------------------------------------------------------------
## both_soi_alpha
## n missing distinct Info Mean Gmd .05 .10
## 1319513 1523008 501 0.999 3.091 0.6139 2.50 2.53
## .25 .50 .75 .90 .95
## 2.65 2.94 3.33 3.99 4.29
##
## lowest : 2.50 2.51 2.52 2.53 2.54, highest: 7.88 7.94 7.95 8.00 9.00
## ---------------------------------------------------------------------------
## both_od_alpha
## n missing distinct Info Mean Gmd
## 1319513 1523008 7 0.656 1.426 0.6452
##
## Value 1 2 3 4 5 6 7
## Frequency 915364 278194 98368 23520 3753 307 7
## Proportion 0.694 0.211 0.075 0.018 0.003 0.000 0.000
## ---------------------------------------------------------------------------
## both_minutes
## n missing distinct Info Mean Gmd .05 .10
## 1319513 1523008 301 0.997 243.1 359.5 -60 -60
## .25 .50 .75 .90 .95
## 5 80 375 840 1075
##
## lowest : -60 -55 -50 -45 -40, highest: 1420 1425 1430 1435 1440
## ---------------------------------------------------------------------------
## soi_alteredmentalstatus
## n missing distinct Info Sum Mean Gmd
## 1670335 1172186 2 0.136 79212 0.04742 0.09035
##
## ---------------------------------------------------------------------------
## soi_glucose
## n missing distinct Info Mean Gmd .05 .10
## 1670335 1172186 121 0.866 0.5885 0.4758 0.0000 0.0000
## .25 .50 .75 .90 .95
## 0.0000 0.8667 1.0000 1.0000 1.0000
##
## lowest : 0.00000000 0.01000000 0.02000000 0.03000000 0.03333333
## highest: 0.96666667 0.97000000 0.98000000 0.99000000 1.00000000
## ---------------------------------------------------------------------------
## soi_heartrate
## n missing distinct Info Mean Gmd .05 .10
## 1670335 1172186 22 0.896 0.6656 0.4201 0.0 0.0
## .25 .50 .75 .90 .95
## 0.3 0.9 1.0 1.0 1.0
##
## lowest : 0.000 0.050 0.100 0.150 0.200, highest: 0.850 0.900 0.925 0.950 1.000
## ---------------------------------------------------------------------------
## soi_inr
## n missing distinct Info Mean Gmd .05 .10
## 1670335 1172186 154 0.571 0.1618 0.267 0 0
## .25 .50 .75 .90 .95
## 0 0 0 1 1
##
## lowest : 0.00000000 0.01333333 0.01666667 0.02000000 0.03333333
## highest: 0.96666667 0.98333333 0.99666667 0.99833333 1.00000000
## ---------------------------------------------------------------------------
## soi_respiratoryrate
## n missing distinct Info Mean Gmd .05 .10
## 1670335 1172186 64 0.96 0.6453 0.3911 0.0000 0.0000
## .25 .50 .75 .90 .95
## 0.4167 0.7500 1.0000 1.0000 1.0000
##
## lowest : 0.000000000 0.008333333 0.027777778 0.041666667 0.083333333
## highest: 0.944444444 0.958333333 0.972222222 0.983333333 1.000000000
## ---------------------------------------------------------------------------
## soi_temperature
## n missing distinct Info Mean Gmd .05 .10
## 1670335 1172186 309 0.689 0.152 0.244 0.0000 0.0000
## .25 .50 .75 .90 .95
## 0.0000 0.0000 0.1765 0.6471 1.0000
##
## lowest : 0.000000000 0.001764706 0.016470588 0.028000000 0.029411765
## highest: 0.980588235 0.982235294 0.982352941 0.997160000 1.000000000
## ---------------------------------------------------------------------------
## soi_bands
## n missing distinct Info Mean Gmd .05 .10
## 1670335 1172186 304 0.187 0.0553 0.1044 0.0000 0.0000
## .25 .50 .75 .90 .95
## 0.0000 0.0000 0.0000 0.0000 0.6667
##
## lowest : 0.00000000 0.00500000 0.01166667 0.01666667 0.01833333
## highest: 0.97833333 0.98000000 0.98333333 0.99833333 1.00000000
## ---------------------------------------------------------------------------
## soi_wbc
## n missing distinct Info Mean Gmd .05 .10
## 1670335 1172186 602 0.94 0.5357 0.4702 0.0000 0.0000
## .25 .50 .75 .90 .95
## 0.0000 0.5933 1.0000 1.0000 1.0000
##
## lowest : 0.000000000 0.001666667 0.003333333 0.005000000 0.006666667
## highest: 0.993333333 0.995000000 0.996666667 0.998333333 1.000000000
## ---------------------------------------------------------------------------
## soi_lactate
## n missing distinct Info Sum Mean Gmd
## 1670335 1172186 2 0.325 206734 0.1238 0.2169
##
## ---------------------------------------------------------------------------
## od_liver
## n missing distinct Info Sum Mean Gmd
## 2107497 735024 2 0.307 244230 0.1159 0.2049
##
## ---------------------------------------------------------------------------
## od_cardiovascular
## n missing distinct Info Sum Mean Gmd
## 2107497 735024 2 0.738 1186809 0.5631 0.492
##
## ---------------------------------------------------------------------------
## od_respiratory
## n missing distinct Info Sum Mean Gmd
## 2107497 735024 2 0.413 347194 0.1647 0.2752
##
## ---------------------------------------------------------------------------
## od_kidney
## n missing distinct Info Sum Mean Gmd
## 2107497 735024 2 0.19 142849 0.06778 0.1264
##
## ---------------------------------------------------------------------------
## od_lactate
## n missing distinct Info Sum Mean Gmd
## 2107497 735024 2 0.258 199997 0.0949 0.1718
##
## ---------------------------------------------------------------------------
## od_metabolic
## n missing distinct Info Sum Mean Gmd
## 2107497 735024 2 0.369 303131 0.1438 0.2463
##
## ---------------------------------------------------------------------------
## od_hematologic
## n missing distinct Info Sum Mean Gmd
## 2107497 735024 2 0.018 12839 0.006092 0.01211
##
## ---------------------------------------------------------------------------
## both_soi_alteredmentalstatus
## n missing distinct Info Sum Mean Gmd
## 1319513 1523008 2 0.119 54680 0.04144 0.07944
##
## ---------------------------------------------------------------------------
## both_soi_glucose
## n missing distinct Info Mean Gmd .05 .10
## 1319513 1523008 121 0.865 0.5751 0.481 0.0000 0.0000
## .25 .50 .75 .90 .95
## 0.0000 0.8333 1.0000 1.0000 1.0000
##
## lowest : 0.00000000 0.01000000 0.02000000 0.03000000 0.03333333
## highest: 0.96666667 0.97000000 0.98000000 0.99000000 1.00000000
## ---------------------------------------------------------------------------
## both_soi_heartrate
## n missing distinct Info Mean Gmd .05 .10
## 1319513 1523008 22 0.885 0.6672 0.422 0.0 0.0
## .25 .50 .75 .90 .95
## 0.3 0.9 1.0 1.0 1.0
##
## lowest : 0.000 0.050 0.100 0.150 0.200, highest: 0.850 0.900 0.925 0.950 1.000
## ---------------------------------------------------------------------------
## both_soi_inr
## n missing distinct Info Mean Gmd .05 .10
## 1319513 1523008 141 0.632 0.186 0.2969 0.0000 0.0000
## .25 .50 .75 .90 .95
## 0.0000 0.0000 0.1667 1.0000 1.0000
##
## lowest : 0.00000000 0.01666667 0.02000000 0.03333333 0.03833333
## highest: 0.95000000 0.96666667 0.98333333 0.99833333 1.00000000
## ---------------------------------------------------------------------------
## both_soi_respiratoryrate
## n missing distinct Info Mean Gmd .05 .10
## 1319513 1523008 61 0.954 0.6495 0.3954 0.0000 0.0000
## .25 .50 .75 .90 .95
## 0.4167 0.7500 1.0000 1.0000 1.0000
##
## lowest : 0.000000000 0.008333333 0.027777778 0.041666667 0.055555556
## highest: 0.933333333 0.944444444 0.958333333 0.972222222 1.000000000
## ---------------------------------------------------------------------------
## both_soi_temperature
## n missing distinct Info Mean Gmd .05 .10
## 1319513 1523008 300 0.716 0.1635 0.2584 0.0 0.0
## .25 .50 .75 .90 .95
## 0.0 0.0 0.2 0.7 1.0
##
## lowest : 0.000000000 0.001764706 0.028000000 0.029411765 0.031176471
## highest: 0.980588235 0.982235294 0.982352941 0.997160000 1.000000000
## ---------------------------------------------------------------------------
## both_soi_bands
## n missing distinct Info Mean Gmd .05 .10
## 1319513 1523008 272 0.217 0.06554 0.1223 0 0
## .25 .50 .75 .90 .95
## 0 0 0 0 1
##
## lowest : 0.000000000 0.005000000 0.008333333 0.011666667 0.016666667
## highest: 0.966666667 0.980000000 0.983333333 0.998333333 1.000000000
## ---------------------------------------------------------------------------
## both_soi_wbc
## n missing distinct Info Mean Gmd .05 .10
## 1319513 1523008 602 0.932 0.5755 0.462 0.0000 0.0000
## .25 .50 .75 .90 .95
## 0.0500 0.6833 1.0000 1.0000 1.0000
##
## lowest : 0.000000000 0.001666667 0.003333333 0.005000000 0.006666667
## highest: 0.993333333 0.995000000 0.996666667 0.998333333 1.000000000
## ---------------------------------------------------------------------------
## both_soi_lactate
## n missing distinct Info Sum Mean Gmd
## 1319513 1523008 2 0.417 220210 0.1669 0.2781
##
## ---------------------------------------------------------------------------
## both_od_liver
## n missing distinct Info Sum Mean Gmd
## 1319513 1523008 2 0.425 225493 0.1709 0.2834
##
## ---------------------------------------------------------------------------
## both_od_cardiovascular
## n missing distinct Info Sum Mean Gmd
## 1319513 1523008 2 0.744 720954 0.5464 0.4957
##
## ---------------------------------------------------------------------------
## both_od_respiratory
## n missing distinct Info Sum Mean Gmd
## 1319513 1523008 2 0.553 321698 0.2438 0.3687
##
## ---------------------------------------------------------------------------
## both_od_kidney
## n missing distinct Info Sum Mean Gmd
## 1319513 1523008 2 0.201 95231 0.07217 0.1339
##
## ---------------------------------------------------------------------------
## both_od_lactate
## n missing distinct Info Sum Mean Gmd
## 1319513 1523008 2 0.417 220210 0.1669 0.2781
##
## ---------------------------------------------------------------------------
## both_od_metabolic
## n missing distinct Info Sum Mean Gmd
## 1319513 1523008 2 0.505 282908 0.2144 0.3369
##
## ---------------------------------------------------------------------------
## both_od_hematologic
## n missing distinct Info Sum Mean Gmd
## 1319513 1523008 2 0.034 15098 0.01144 0.02262
##
## ---------------------------------------------------------------------------
## patientweight
## n missing distinct Info Mean Gmd .05 .10
## 2600179 242342 17020 1 83.24 27.65 49.50 55.00
## .25 .50 .75 .90 .95
## 65.70 79.42 96.00 114.90 129.50
##
## lowest : 0.00 0.09 0.17 0.20 0.22, highest: 956.00 967.00 969.00 992.50 993.70
## ---------------------------------------------------------------------------
## BMI
## n missing distinct Info Mean Gmd .05 .10
## 2532267 310254 308878 1 Inf NaN 18.47 20.22
## .25 .50 .75 .90 .95
## 23.39 27.44 32.69 39.36 44.82
##
## Value 0.0e+00 1.0e+06 2.0e+06 8.0e+06 9.0e+06 1.3e+07 3.1e+07 3.4e+07
## Frequency 2530160 81 4 1 1 1 1 1
## Proportion 0.999 0.000 0.000 0.000 0.000 0.000 0.000 0.000
##
## Value 8.6e+07 Inf
## Frequency 1 2016
## Proportion 0.000 0.001
## ---------------------------------------------------------------------------
## BMI_Ranges
## n missing distinct
## 2842521 0 5
##
## Value (0,18.5] (18.5,25] (25,35] (35,200]
## Frequency 128213 753213 1191774 453265
## Proportion 0.045 0.265 0.419 0.159
##
## Value Other/Unknown
## Frequency 316056
## Proportion 0.111
## ---------------------------------------------------------------------------
## age_Ranges
## n missing distinct
## 2839897 2624 8
##
## Value (0,25] (25,35] (35,45] (45,55] (55,65] (65,75] (75,85]
## Frequency 105109 141150 215032 421325 585296 621393 526359
## Proportion 0.037 0.050 0.076 0.148 0.206 0.219 0.185
##
## Value (85,100]
## Frequency 224233
## Proportion 0.079
## ---------------------------------------------------------------------------
## hospitalLOS_Ranges
## n missing distinct
## 2839140 3381 10
##
## Value (0,1] (1,3] (3,5] (5,10] (10,20] (20,30]
## Frequency 150460 582206 529927 820698 507248 143837
## Proportion 0.053 0.205 0.187 0.289 0.179 0.051
##
## Value (30,60] (60,90] (90,150] (150,999]
## Frequency 85601 12058 4741 2364
## Proportion 0.030 0.004 0.002 0.001
## ---------------------------------------------------------------------------
## icuLOS_Ranges
## n missing distinct
## 2826779 15742 8
##
## Value (0,1] (1,3] (3,5] (5,10] (10,20] (20,30] (30,60]
## Frequency 928888 1168923 352746 247099 99566 20292 8379
## Proportion 0.329 0.414 0.125 0.087 0.035 0.007 0.003
##
## Value (60,999]
## Frequency 886
## Proportion 0.000
## ---------------------------------------------------------------------------
## ethnicity2
## n missing distinct
## 2842521 0 6
##
## Value Caucasian African American Hispanic
## Frequency 2152704 304105 145350
## Proportion 0.757 0.107 0.051
##
## Value Asian Native American Other/Unknown
## Frequency 45050 25711 169601
## Proportion 0.016 0.009 0.060
## ---------------------------------------------------------------------------
## gender2
## n missing distinct
## 2842521 0 3
##
## Value Male Female Other/Unknown
## Frequency 1527370 1309647 5504
## Proportion 0.537 0.461 0.002
## ---------------------------------------------------------------------------
## hospital_region2
## n missing distinct
## 2842521 0 5
##
## Value Midwest Northeast South West Unknown
## Frequency 753120 165767 714254 576418 632962
## Proportion 0.265 0.058 0.251 0.203 0.223
## ---------------------------------------------------------------------------
## sepsis_outcome
## n missing distinct
## 2391341 451180 2
##
## Value FALSE TRUE
## Frequency 1906183 485158
## Proportion 0.797 0.203
## ---------------------------------------------------------------------------
## group
## n missing distinct
## 2833373 9148 12
##
## Cardiovascular (839352, 0.296), Gastrointestinal (266781, 0.094),
## Gynaecological (6754, 0.002), Hematological (18705, 0.007), Metabolic
## (193873, 0.068), Muscoskeletal/Skin disease (35740, 0.013), Neurological
## (323997, 0.114), Renal/Genitourinary (61926, 0.022), Respiratory (381474,
## 0.135), Sepsis (571651, 0.202), Trauma (111731, 0.039), Undefined (21389,
## 0.008)
## ---------------------------------------------------------------------------
## post.operative
## n missing distinct Info Sum Mean Gmd
## 2833373 9148 2 0.423 480702 0.1697 0.2817
##
## ---------------------------------------------------------------------------
## code
## n missing distinct Info Mean Gmd .05 .10
## 2833373 9148 379 0.998 527.3 454.5 104 106
## .25 .50 .75 .90 .95
## 206 410 702 1208 1408
##
## lowest : 0.01 0.02 0.03 0.04 0.05
## highest: 2201.01 2201.02 2201.03 2201.04 2201.05
## ---------------------------------------------------------------------------
## dx
## n missing distinct
## 2833373 9148 379
##
## lowest : Abdomen/extremity trauma Abdomen/face trauma Abdomen/multiple trauma Abdomen only trauma Abdomen/pelvis trauma
## highest: Vena cava clipping Vena cava filer insertion Ventriculostomy Weaning from mechanical ventilation (transfer from other unit or hospital only) Whipple surgery for pancreatic cancer
## ---------------------------------------------------------------------------
## number
## n missing distinct Info Mean Gmd
## 2833373 9148 6 0.155 1.134 0.2576
##
## Value 1 2 3 4 5 6
## Frequency 2679142 48853 30056 41793 22294 11235
## Proportion 0.946 0.017 0.011 0.015 0.008 0.004
## ---------------------------------------------------------------------------
## admitdiagnosis
## n missing distinct
## 2833373 9148 402
##
## lowest : ACIDBASE ACUHEPFAIL ADDISON ADRENNEO AIROBSTRX
## highest: UNSTANGINA VARICBLEED VASCULITIS VIRALMYOSI WEANVENT
## ---------------------------------------------------------------------------
## admitdxpath
## n missing distinct
## 2833373 9148 402
##
## lowest : admission diagnosis|All Diagnosis|Non-operative|Diagnosis|Cardiovascular|Anaphylaxis admission diagnosis|All Diagnosis|Non-operative|Diagnosis|Cardiovascular|Aneurysm, dissecting aortic admission diagnosis|All Diagnosis|Non-operative|Diagnosis|Cardiovascular|Aneurysm/pseudoaneurysm, other admission diagnosis|All Diagnosis|Non-operative|Diagnosis|Cardiovascular|Angina, stable (asymp or stable pattern of symptoms w/meds)
## highest: admission diagnosis|All Diagnosis|Operative|Diagnosis|Trauma|Extremity/multiple trauma, surgery for admission diagnosis|All Diagnosis|Operative|Diagnosis|Trauma|Extremity only trauma, surgery for admission diagnosis|All Diagnosis|Operative|Diagnosis|Trauma|Face/multiple trauma, surgery for admission diagnosis|All Diagnosis|Operative|Diagnosis|Trauma|Face only trauma, surgery for admission diagnosis|All Diagnosis|Operative|Diagnosis|Trauma|Trauma surgery, other
## ---------------------------------------------------------------------------
## numobs
## n missing distinct Info Mean Gmd .05 .10
## 2512032 330489 235 1 2519 2558 43 129
## .25 .50 .75 .90 .95
## 484 1819 4354 6262 6790
##
## lowest : 0 1 2 3 4, highest: 5003 5989 6262 6790 8375
## ---------------------------------------------------------------------------
## possible.group
## n missing distinct Info Mean Gmd
## 20200 2822321 8 0.887 975.9 602.3
##
## Value 312.00 408.02 602.09 802.00 1208.00 1504.00 1701.00 1705.03
## Frequency 6838 1331 66 1188 1258 8471 446 602
## Proportion 0.339 0.066 0.003 0.059 0.062 0.419 0.022 0.030
## ---------------------------------------------------------------------------
## X
## n missing distinct
## 2833373 9148 13
##
## lowest : ANZICS addition ANZICS Addition. Sub-categories won’t map well, but collapsing to hierarchy (1206) should work ANZICS addition – we have invented this diagnosis code assumes admitted in eICU due to rejection
## highest: Chest pain, unknown origin fuzzy match multiple matches presumably ANZICS only allows the surgical version of this code there are 6 categories for this in eICU
## ---------------------------------------------------------------------------
## c_temp_min
## n missing distinct Info Mean Gmd .05 .10
## 2522673 319848 1765 0.996 36.42 0.9129 35.2 35.6
## .25 .50 .75 .90 .95
## 36.1 36.4 36.7 37.0 37.2
##
## lowest : 0.10 0.20 0.50 0.60 0.75, highest: 103.00 103.20 103.30 103.50 108.30
## ---------------------------------------------------------------------------
## c_temp_max
## n missing distinct Info Mean Gmd .05 .10
## 2522673 319848 1226 0.997 37.31 0.9948 36.2 36.5
## .25 .50 .75 .90 .95
## 36.8 37.1 37.6 38.2 38.7
##
## lowest : 0.10 2.00 4.70 11.00 11.85, highest: 110.00 110.40 111.20 112.05 112.60
## ---------------------------------------------------------------------------
## c_HR_max
## n missing distinct Info Mean Gmd .05 .10
## 2730479 112042 314 1 101.4 25.05 68 74
## .25 .50 .75 .90 .95
## 86 99 115 131 141
##
## lowest : 1 2 3 5 6, highest: 374 379 380 383 387
## ---------------------------------------------------------------------------
## c_resp_max
## n missing distinct Info Mean Gmd .05 .10
## 2707796 134725 201 0.998 26.98 9.668 16 18
## .25 .50 .75 .90 .95
## 21 25 30 38 44
##
## lowest : 1 2 3 4 5, highest: 194 196 197 199 200
## ---------------------------------------------------------------------------
## c_sbp_min
## n missing distinct Info Mean Gmd .05 .10
## 2643599 198922 299 1 92.01 29.63 48 58
## .25 .50 .75 .90 .95
## 75 92 109 125 136
##
## lowest : 1 2 3 4 5, highest: 290 294 302 313 347
## ---------------------------------------------------------------------------
## c_mbp_min
## n missing distinct Info Mean Gmd .05 .10
## 2592405 250116 680 1 70.12 24.33 42 47
## .25 .50 .75 .90 .95
## 56 66 78 97 120
##
## lowest : 0.13 0.56 0.61 0.74 0.87, highest: 293.00 318.00 325.00 347.00 359.00
## ---------------------------------------------------------------------------
## icu_admit_source2
## n missing distinct
## 2842521 0 6
##
## Value Floor OR/Proc Area Direct Admit
## Frequency 435214 494766 241396
## Proportion 0.153 0.174 0.085
##
## Value Emergency Department Other Step-Down Unit
## Frequency 1245659 183843 241643
## Proportion 0.438 0.065 0.085
## ---------------------------------------------------------------------------
## icu_type2
## n missing distinct
## 2842521 0 8
##
## Trauma ICU (36823, 0.013), Cardiac Care ICU (192048, 0.068),
## Cardiac/Surgical Care ICU (437527, 0.154), Medical/Surgical ICU (1527054,
## 0.537), Medical ICU (248339, 0.087), Other ICU (56590, 0.020), Neuro ICU
## (164626, 0.058), Surgical ICU (179514, 0.063)
## ---------------------------------------------------------------------------
## icu_disch_location2
## n missing distinct
## 2842521 0 7
##
## Value Floor Death Home SNF/Rehab
## Frequency 1850937 154009 250587 34591
## Proportion 0.651 0.054 0.088 0.012
##
## Value Other Other Hospital Step-Down Unit
## Frequency 202328 58896 291173
## Proportion 0.071 0.021 0.102
## ---------------------------------------------------------------------------
## physicianSpeciality2
## n missing distinct
## 2842521 0 2
##
## Value Critical Care Speciality-Other
## Frequency 473200 2369321
## Proportion 0.166 0.834
## ---------------------------------------------------------------------------
## sofa_respiration_baseline2
## n missing distinct
## 2842521 0 2
##
## Value FALSE TRUE
## Frequency 2269755 572766
## Proportion 0.799 0.201
## ---------------------------------------------------------------------------
## sofa_renal_baseline2
## n missing distinct
## 2842521 0 2
##
## Value FALSE TRUE
## Frequency 2754112 88409
## Proportion 0.969 0.031
## ---------------------------------------------------------------------------
## sofa_liver_baseline2
## n missing distinct
## 2842521 0 2
##
## Value FALSE TRUE
## Frequency 2792493 50028
## Proportion 0.982 0.018
## ---------------------------------------------------------------------------
## SOFA_Change
## n missing distinct Info Mean Gmd .05 .10
## 2842521 0 24 0.976 2.975 2.964 0 0
## .25 .50 .75 .90 .95
## 1 2 4 7 9
##
## lowest : 0 1 2 3 4, highest: 19 20 21 22 23
## ---------------------------------------------------------------------------
## SOFA_Positive
## n missing distinct
## 2842521 0 2
##
## Value FALSE TRUE
## Frequency 1141836 1700685
## Proportion 0.402 0.598
## ---------------------------------------------------------------------------
## SOFA_Score
## n missing distinct Info Mean Gmd .05 .10
## 2842521 0 24 0.979 3.183 3.164 0 0
## .25 .50 .75 .90 .95
## 1 2 5 7 9
##
## lowest : 0 1 2 3 4, highest: 19 20 21 22 23
## ---------------------------------------------------------------------------
## SOFA_Positive2
## n missing distinct
## 2842521 0 2
##
## Value FALSE TRUE
## Frequency 1092979 1749542
## Proportion 0.385 0.615
## ---------------------------------------------------------------------------
## GCS_qSOFA
## n missing distinct
## 2437440 405081 2
##
## Value FALSE TRUE
## Frequency 1536220 901220
## Proportion 0.63 0.37
## ---------------------------------------------------------------------------
## BP_qSOFA
## n missing distinct
## 2643599 198922 2
##
## Value FALSE TRUE
## Frequency 961957 1681642
## Proportion 0.364 0.636
## ---------------------------------------------------------------------------
## Resp_qSOFA
## n missing distinct
## 2707796 134725 2
##
## Value FALSE TRUE
## Frequency 760333 1947463
## Proportion 0.281 0.719
## ---------------------------------------------------------------------------
## qSOFA_total
## n missing distinct Info Mean Gmd
## 2842521 0 4 0.905 1.594 1.016
##
## Value 0 1 2 3
## Frequency 401017 835190 1123807 482507
## Proportion 0.141 0.294 0.395 0.170
## ---------------------------------------------------------------------------
## qSOFA_Positive
## n missing distinct
## 2842521 0 2
##
## Value FALSE TRUE
## Frequency 1236207 1606314
## Proportion 0.435 0.565
## ---------------------------------------------------------------------------
## temp_SIRS
## n missing distinct
## 2522673 319848 2
##
## Value FALSE TRUE
## Frequency 1798187 724486
## Proportion 0.713 0.287
## ---------------------------------------------------------------------------
## wbc_SIRS
## n missing distinct
## 2291983 550538 2
##
## Value FALSE TRUE
## Frequency 1240013 1051970
## Proportion 0.541 0.459
## ---------------------------------------------------------------------------
## resp_SIRS
## n missing distinct
## 2723605 118916 2
##
## Value FALSE TRUE
## Frequency 591013 2132592
## Proportion 0.217 0.783
## ---------------------------------------------------------------------------
## HR_SIRS
## n missing distinct
## 2730479 112042 2
##
## Value FALSE TRUE
## Frequency 925082 1805397
## Proportion 0.339 0.661
## ---------------------------------------------------------------------------
## SIRS_total
## n missing distinct Info Mean Gmd
## 2842521 0 5 0.934 2.01 1.247
##
## Value 0 1 2 3 4
## Frequency 310612 593666 954052 724089 260102
## Proportion 0.109 0.209 0.336 0.255 0.092
## ---------------------------------------------------------------------------
## SIRS_Positive
## n missing distinct
## 2842521 0 2
##
## Value FALSE TRUE
## Frequency 904278 1938243
## Proportion 0.318 0.682
## ---------------------------------------------------------------------------
## StickyMinutes
## n missing distinct Info Mean Gmd .05 .10
## 1422699 1419822 301 0.998 270.4 382.6 -60 -60
## .25 .50 .75 .90 .95
## 5 100 440 890 1110
##
## lowest : -60 -55 -50 -45 -40, highest: 1420 1425 1430 1435 1440
## ---------------------------------------------------------------------------
## FuzzyTotal1
## n missing distinct Info Mean Gmd
## 2842521 0 3 0.834 1.329 0.7841
##
## Value 0 1 2
## Frequency 487388 932434 1422699
## Proportion 0.171 0.328 0.501
## ---------------------------------------------------------------------------
## SimultaneousMinutes
## n missing distinct
## 2842521 0 2
##
## Value FALSE TRUE
## Frequency 1523008 1319513
## Proportion 0.536 0.464
## ---------------------------------------------------------------------------
## SepsisFuzzyLogicPositive
## n missing distinct
## 2842521 0 2
##
## Value FALSE TRUE
## Frequency 1523008 1319513
## Proportion 0.536 0.464
## ---------------------------------------------------------------------------
## SepsisFuzzyLogicPositive2
## n missing distinct
## 2842521 0 2
##
## Value FALSE TRUE
## Frequency 1523008 1319513
## Proportion 0.536 0.464
## ---------------------------------------------------------------------------
## hasDiagnosisCodes
## n missing distinct
## 2842521 0 2
##
## Value FALSE TRUE
## Frequency 451180 2391341
## Proportion 0.159 0.841
## ---------------------------------------------------------------------------
## inclusiongroup
## n missing distinct Info Sum Mean Gmd
## 2842521 0 2 0.654 912514 0.321 0.4359
##
## ---------------------------------------------------------------------------
##
## Variables with all observations missing:
##
## [1] hospital_type icu_sizedescribe(ssd_incl)## Warning in w * sort(x - mean(x)): longer object length is not a multiple of
## shorter object length## ssd_incl
##
## 295 Variables 912509 Observations
## ---------------------------------------------------------------------------
## patientunitstayid
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 912509 1 1758473 1107580 244862 371830
## .25 .50 .75 .90 .95
## 1014642 1702955 2585746 3107552 3214507
##
## lowest : 141136 141137 141139 141141 141142
## highest: 3353265 3353266 3353268 3353269 3353271
## ---------------------------------------------------------------------------
## exclusion_over18
## n missing distinct Info Mean Gmd
## 912509 0 1 0 0 0
##
## Value 0
## Frequency 912509
## Proportion 1
## ---------------------------------------------------------------------------
## exclusion_firstadmission
## n missing distinct Info Mean Gmd
## 912509 0 1 0 0 0
##
## Value 0
## Frequency 912509
## Proportion 1
## ---------------------------------------------------------------------------
## exclusion_yearfilter
## n missing distinct Info Mean Gmd
## 912509 0 1 0 0 0
##
## Value 0
## Frequency 912509
## Proportion 1
## ---------------------------------------------------------------------------
## exclusion_apacheiva
## n missing distinct Info Mean Gmd
## 912509 0 1 0 0 0
##
## Value 0
## Frequency 912509
## Proportion 1
## ---------------------------------------------------------------------------
## exclusion_vitalobservations
## n missing distinct Info Mean Gmd
## 912509 0 1 0 0 0
##
## Value 0
## Frequency 912509
## Proportion 1
## ---------------------------------------------------------------------------
## exclusion_labobservations
## n missing distinct Info Mean Gmd
## 912509 0 1 0 0 0
##
## Value 0
## Frequency 912509
## Proportion 1
## ---------------------------------------------------------------------------
## exclusion_medobservations
## n missing distinct Info Mean Gmd
## 912509 0 1 0 0 0
##
## Value 0
## Frequency 912509
## Proportion 1
## ---------------------------------------------------------------------------
## hospitalid
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 183 1 271.7 127.2 79 122
## .25 .50 .75 .90 .95
## 188 264 358 421 449
##
## lowest : 56 58 59 60 61, highest: 447 449 452 458 459
## ---------------------------------------------------------------------------
## gender
## n missing distinct
## 912509 0 5
##
## Value Female Male Other Unknown
## Frequency 53 421748 490533 26 149
## Proportion 0.000 0.462 0.538 0.000 0.000
## ---------------------------------------------------------------------------
## age
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 73 1 62.94 19.34 29 38
## .25 .50 .75 .90 .95
## 52 65 76 84 88
##
## lowest : 18 19 20 21 22, highest: 86 87 88 89 90
## ---------------------------------------------------------------------------
## ethnicity
## n missing distinct
## 912509 0 7
##
## (11604, 0.013), African American (105292, 0.115), Asian (11695, 0.013),
## Caucasian (695367, 0.762), Hispanic (41393, 0.045), Native American (6765,
## 0.007), Other/Unknown (40393, 0.044)
## ---------------------------------------------------------------------------
## hospital_los
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 57044 1 7.716 7.273 1.035 1.574
## .25 .50 .75 .90 .95
## 2.877 5.299 9.396 15.976 21.925
##
## lowest : 3.194444e-02 3.958333e-02 5.208333e-02 8.333333e-02 9.027778e-02
## highest: 9.192007e+02 9.810410e+02 1.099160e+03 1.190723e+03 1.224962e+03
## ---------------------------------------------------------------------------
## hospital_size
## n missing distinct
## 912509 0 5
##
## Value <100 100-249 250-500 >500
## Frequency 72678 36772 207117 167113 428829
## Proportion 0.080 0.040 0.227 0.183 0.470
## ---------------------------------------------------------------------------
## hospital_teaching_status
## n missing distinct
## 912509 0 3
##
## Value f t
## Frequency 37915 598042 276552
## Proportion 0.042 0.655 0.303
## ---------------------------------------------------------------------------
## hospital_region
## n missing distinct
## 912509 0 5
##
## Value Midwest Northeast South West
## Frequency 55141 383075 73523 283987 116783
## Proportion 0.060 0.420 0.081 0.311 0.128
## ---------------------------------------------------------------------------
## hospital_discharge_disposition
## n missing distinct
## 912509 0 7
##
## Value Death Home NursingHome Other
## Frequency 86219 560422 49569 25746
## Proportion 0.094 0.614 0.054 0.028
##
## Value OtherExternal OtherHospital SNF
## Frequency 41679 37692 111182
## Proportion 0.046 0.041 0.122
## ---------------------------------------------------------------------------
## hospital_mortality
## n missing distinct
## 912509 0 2
##
## Value 0 1
## Frequency 826290 86219
## Proportion 0.906 0.094
## ---------------------------------------------------------------------------
## hospital_mortality_ultimate
## n missing distinct
## 912509 0 2
##
## Value 0 1
## Frequency 826290 86219
## Proportion 0.906 0.094
## ---------------------------------------------------------------------------
## hospitaladmityear
## n missing distinct Info Mean Gmd
## 912509 0 7 0.97 2013 1.888
##
## Value 2009 2010 2011 2012 2013 2014 2015
## Frequency 1331 112863 122110 149856 167202 178896 180251
## Proportion 0.001 0.124 0.134 0.164 0.183 0.196 0.198
## ---------------------------------------------------------------------------
## hospitaldischargeyear
## n missing distinct
## 912509 0 6
##
## Value -2010 2011 2012 2013 2014 2015-16
## Frequency 111530 122036 149169 167298 178187 184289
## Proportion 0.122 0.134 0.163 0.183 0.195 0.202
## ---------------------------------------------------------------------------
## icu_los
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 34183 1 3.078 3.151 0.5257 0.7000
## .25 .50 .75 .90 .95
## 1.0118 1.8444 3.3646 6.6014 10.0431
##
## lowest : 0.1666667 0.1673611 0.1680556 0.1687500 0.1694444
## highest: 158.5472222 165.7777778 192.9875000 246.9041667 298.9916667
## ---------------------------------------------------------------------------
## icu_type
## n missing distinct
## 912509 0 11
##
## Cardiac ICU (65472, 0.072), CCU-CTICU (86619, 0.095), CSICU (25733,
## 0.028), CTICU (28922, 0.032), Floating (Universal) License ICU (2596,
## 0.003), Med-Surg ICU (468867, 0.514), MICU (86772, 0.095), Neuro ICU
## (71250, 0.078), SICU (65312, 0.072), Trauma ICU (10946, 0.012), Vent ICU
## (20, 0.000)
## ---------------------------------------------------------------------------
## icu_admit_source
## n missing distinct
## 912509 0 16
##
## (1301, 0.001), Acute Care/Floor (11475, 0.013), Chest Pain Center (3394,
## 0.004), Direct Admit (75096, 0.082), Emergency Department (456475, 0.500),
## Floor (143161, 0.157), ICU (286, 0.000), ICU to SDU (577, 0.001),
## Observation (26, 0.000), Operating Room (124573, 0.137), Other (21,
## 0.000), Other Hospital (22942, 0.025), Other ICU (6129, 0.007), PACU
## (3881, 0.004), Recovery Room (44595, 0.049), Step-Down Unit (SDU) (18577,
## 0.020)
## ---------------------------------------------------------------------------
## icu_disch_location
## n missing distinct
## 912509 0 18
##
## (350, 0.000), Acute Care/Floor (44010, 0.048), Death (61357, 0.067), Floor
## (559247, 0.613), Home (88591, 0.097), ICU (42, 0.000), Nursing Home (1118,
## 0.001), Operating Room (7, 0.000), Other (6359, 0.007), Other External
## (16427, 0.018), Other Hospital (20636, 0.023), Other ICU (6129, 0.007),
## Other ICU (CABG) (1, 0.000), Other Internal (1576, 0.002), Rehabilitation
## (4052, 0.004), Skilled Nursing Facility (8946, 0.010), Step-Down Unit
## (SDU) (33478, 0.037), Telemetry (60183, 0.066)
## ---------------------------------------------------------------------------
## icu_mortality
## n missing distinct
## 912456 53 2
##
## Value 0 1
## Frequency 851099 61357
## Proportion 0.933 0.067
## ---------------------------------------------------------------------------
## admitsource
## n missing distinct Info Mean Gmd
## 912509 0 9 0.852 5.857 2.77
##
## Value -1 1 2 3 4 5 6 7 8
## Frequency 1364 124576 44595 3394 162679 5098 22945 75102 472756
## Proportion 0.001 0.137 0.049 0.004 0.178 0.006 0.025 0.082 0.518
## ---------------------------------------------------------------------------
## dischargelocation
## n missing distinct Info Mean Gmd
## 912509 0 7 0.72 5.303 1.818
##
## Value -1 4 5 6 7 8 9
## Frequency 350 593099 5756 20636 88591 142720 61357
## Proportion 0.000 0.650 0.006 0.023 0.097 0.156 0.067
## ---------------------------------------------------------------------------
## bedcount
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 52 0.998 26.08 15.32 10 12
## .25 .50 .75 .90 .95
## 16 22 32 45 62
##
## lowest : 2 3 4 5 6, highest: 60 62 68 71 84
## ---------------------------------------------------------------------------
## readmit
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.145 46464 0.05092 0.09665
##
## ---------------------------------------------------------------------------
## apacheiva
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 212 1 55.54 27.83 23 28
## .25 .50 .75 .90 .95
## 37 51 68 90 106
##
## lowest : 1 2 3 4 5, highest: 208 209 211 214 230
## ---------------------------------------------------------------------------
## apacheadmissiondx
## n missing distinct
## 911985 524 400
##
## lowest : Abdomen/extremity trauma Abdomen/face trauma Abdomen/multiple trauma Abdomen only trauma Abdomen/pelvis trauma
## highest: Vena cava filter insertion Ventricular Septal Defect (VSD) Repair Ventriculostomy Weaning from mechanical ventilation (transfer from other unit or hospital only) Whipple-surgery for pancreatic cancer
## ---------------------------------------------------------------------------
## dialysis
## n missing distinct
## 912509 0 2
##
## Value 0 1
## Frequency 881875 30634
## Proportion 0.966 0.034
## ---------------------------------------------------------------------------
## aids
## n missing distinct
## 912509 0 2
##
## Value 0 1
## Frequency 911619 890
## Proportion 0.999 0.001
## ---------------------------------------------------------------------------
## hepaticfailure
## n missing distinct
## 912509 0 2
##
## Value FALSE TRUE
## Frequency 893444 19065
## Proportion 0.979 0.021
## ---------------------------------------------------------------------------
## cirrhosis
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.043 13319 0.0146 0.02877
##
## ---------------------------------------------------------------------------
## diabetes
## n missing distinct
## 912509 0 2
##
## Value 0 1
## Frequency 712693 199816
## Proportion 0.781 0.219
## ---------------------------------------------------------------------------
## immunosuppression
## n missing distinct
## 912509 0 2
##
## Value 0 1
## Frequency 891128 21381
## Proportion 0.977 0.023
## ---------------------------------------------------------------------------
## leukemia
## n missing distinct
## 912509 0 2
##
## Value 0 1
## Frequency 905925 6584
## Proportion 0.993 0.007
## ---------------------------------------------------------------------------
## lymphoma
## n missing distinct
## 912509 0 2
##
## Value 0 1
## Frequency 908895 3614
## Proportion 0.996 0.004
## ---------------------------------------------------------------------------
## metastaticcancer
## n missing distinct
## 912509 0 2
##
## Value 0 1
## Frequency 895002 17507
## Proportion 0.981 0.019
## ---------------------------------------------------------------------------
## thrombolytics
## n missing distinct
## 912509 0 2
##
## Value 0 1
## Frequency 895774 16735
## Proportion 0.982 0.018
## ---------------------------------------------------------------------------
## admissionheight
## n missing distinct Info Mean Gmd .05 .10
## 889741 22768 1512 0.999 169.5 13.63 152.4 155.0
## .25 .50 .75 .90 .95
## 162.5 170.0 177.8 183.0 187.9
##
## lowest : 0.00 0.66 0.88 0.90 0.91, highest: 670.00 700.00 701.00 702.90 712.20
## ---------------------------------------------------------------------------
## admissionweight
## n missing distinct Info Mean Gmd .05 .10
## 869001 43508 8190 1 83.83 27.63 50.0 55.7
## .25 .50 .75 .90 .95
## 66.1 80.0 96.6 115.5 130.0
##
## lowest : 0.00 0.04 0.09 0.10 0.11, highest: 969.00 970.50 982.00 983.50 987.30
## ---------------------------------------------------------------------------
## chartedweight
## n missing distinct Info Mean Gmd .05 .10
## 548040 364469 11291 1 84.12 27.81 49.80 55.54
## .25 .50 .75 .90 .95
## 66.40 80.50 97.40 116.30 130.60
##
## lowest : 30.00000 30.02779 30.03000 30.07000 30.07315
## highest: 297.00000 298.00000 298.46354 299.37072 299.90000
## ---------------------------------------------------------------------------
## eyes
## n missing distinct Info Mean Gmd
## 912509 0 5 0.65 3.428 0.9003
##
## Value -1 1 2 3 4
## Frequency 9882 83374 43799 135140 640314
## Proportion 0.011 0.091 0.048 0.148 0.702
## ---------------------------------------------------------------------------
## motor
## n missing distinct Info Mean Gmd
## 912509 0 7 0.524 5.393 1.045
##
## Value -1 1 2 3 4 5 6
## Frequency 9882 55220 3985 6251 49127 75881 712163
## Proportion 0.011 0.061 0.004 0.007 0.054 0.083 0.780
## ---------------------------------------------------------------------------
## verbal
## n missing distinct Info Mean Gmd
## 912509 0 6 0.745 3.944 1.538
##
## Value -1 1 2 3 4 5
## Frequency 9882 167720 20933 28514 113272 572188
## Proportion 0.011 0.184 0.023 0.031 0.124 0.627
## ---------------------------------------------------------------------------
## gcs
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 14 0.809 12.76 3.415 3 7
## .25 .50 .75 .90 .95
## 12 15 15 15 15
##
## Value -3 3 4 5 6 7 8 9 10
## Frequency 9882 49468 4676 5010 18944 23458 20484 21959 30397
## Proportion 0.011 0.054 0.005 0.005 0.021 0.026 0.022 0.024 0.033
##
## Value 11 12 13 14 15
## Frequency 28152 23840 44576 108048 523615
## Proportion 0.031 0.026 0.049 0.118 0.574
## ---------------------------------------------------------------------------
## unablegcs
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.032 9882 0.01083 0.02142
##
## ---------------------------------------------------------------------------
## urine
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 68282 0.896 998.4 1383 -1.0 -1.0
## .25 .50 .75 .90 .95
## -1.0 175.7 1609.5 2881.8 3829.8
##
## lowest : -1.0000 0.0000 0.6912 0.7776 0.8640
## highest: 84324.2400 85489.7760 98655.2352 155900.0736 501725.8368
## ---------------------------------------------------------------------------
## pao2_apache
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 3996 0.565 31.19 53.79 -1 -1
## .25 .50 .75 .90 .95
## -1 -1 -1 116 173
##
## lowest : -1.0 2.0 4.0 4.5 9.0, highest: 663.8 664.0 677.0 685.4 686.0
## ---------------------------------------------------------------------------
## fio2_apache
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 197 0.565 13.76 24.1 -1 -1
## .25 .50 .75 .90 .95
## -1 -1 -1 60 100
##
## lowest : -1.0 21.0 22.0 23.0 23.5, highest: 99.6 99.7 99.8 99.9 100.0
## ---------------------------------------------------------------------------
## pao2fio2_apache
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 14034 0.565 57.48 96.84 -1.0 -1.0
## .25 .50 .75 .90 .95
## -1.0 -1.0 -1.0 252.4 342.5
##
## lowest : -1.00000 9.52381 10.00000 11.00000 12.00000
## highest: 2365.21739 2500.00000 2704.76190 2719.04762 2804.76190
## ---------------------------------------------------------------------------
## temperature_apache
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 536 0.997 35.15 3.215 33.90 35.50
## .25 .50 .75 .90 .95
## 36.10 36.40 36.70 37.05 37.33
##
## lowest : -1.00 20.00 20.10 20.20 20.30, highest: 42.66 42.70 42.80 42.90 43.00
## ---------------------------------------------------------------------------
## respiratoryrate_apache
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 134 0.999 24.88 17.09 5 7
## .25 .50 .75 .90 .95
## 10 27 35 45 52
##
## lowest : 4.0 5.0 6.0 6.6 6.7, highest: 57.0 58.0 59.0 59.1 60.0
## ---------------------------------------------------------------------------
## heartrate_apache
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 201 1 100.1 34.69 48 53
## .25 .50 .75 .90 .95
## 87 104 120 136 146
##
## lowest : 20 21 22 23 24, highest: 216 217 218 219 220
## ---------------------------------------------------------------------------
## mbp_apache
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 161 1 85.71 45.43 42 45
## .25 .50 .75 .90 .95
## 53 64 123 146 163
##
## lowest : 40 41 42 43 44, highest: 196 197 198 199 200
## ---------------------------------------------------------------------------
## albumin_apache
## n missing distinct Info Mean Gmd .05 .10
## 363837 548672 63 0.998 2.92 0.7948 1.7 2.0
## .25 .50 .75 .90 .95
## 2.4 2.9 3.4 3.8 4.0
##
## lowest : 1.0 1.1 1.2 1.3 1.4, highest: 6.3 6.7 6.9 7.0 8.2
## ---------------------------------------------------------------------------
## bilirubin_apache
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 966 0.745 -0.1945 1.194 -1.0 -1.0
## .25 .50 .75 .90 .95
## -1.0 -1.0 0.5 1.0 1.7
##
## lowest : -1.00 0.05 0.09 0.10 0.11, highest: 60.30 61.50 63.10 64.00 72.40
## ---------------------------------------------------------------------------
## bun_apache
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 944 0.992 21.28 22.29 -1 -1
## .25 .50 .75 .90 .95
## 8 16 28 49 66
##
## lowest : -1.0 1.0 2.0 2.3 2.5, highest: 251.0 252.0 253.0 254.0 255.0
## ---------------------------------------------------------------------------
## creatinine_apache
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 2398 0.993 1.05 1.628 -1.00 -1.00
## .25 .50 .75 .90 .95
## 0.53 0.84 1.38 2.57 4.08
##
## lowest : -1.00 0.10 0.11 0.12 0.13, highest: 24.89 24.91 24.94 24.95 25.00
## ---------------------------------------------------------------------------
## glucose_apache
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 1384 0.999 148.1 110.2 -1 -1
## .25 .50 .75 .90 .95
## 89 121 194 275 342
##
## lowest : -1.0 1.0 1.1 1.3 1.5, highest: 2356.0 2357.0 2796.0 2810.0 2954.0
## ---------------------------------------------------------------------------
## hematocrit_apache
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 612 0.992 25.91 15.7 -1.0 -1.0
## .25 .50 .75 .90 .95
## 22.3 30.3 36.1 40.4 42.8
##
## lowest : -1.0 5.0 5.1 5.9 6.0, highest: 70.2 70.8 71.0 72.7 78.0
## ---------------------------------------------------------------------------
## sodium_apache
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 253 0.991 112.2 45.42 -1 -1
## .25 .50 .75 .90 .95
## 131 137 140 142 145
##
## lowest : -1 88 90 91 95, highest: 190 192 194 196 198
## ---------------------------------------------------------------------------
## paco2_apache
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 1164 0.565 9.506 16.71 -1 -1
## .25 .50 .75 .90 .95
## -1 -1 -1 42 49
##
## lowest : -1.0 3.1 6.9 7.0 7.3, highest: 147.7 147.8 148.0 148.8 150.0
## ---------------------------------------------------------------------------
## ph_apache
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 967 0.565 1.025 3.076 -1.000 -1.000
## .25 .50 .75 .90 .95
## -1.000 -1.000 -1.000 7.390 7.435
##
## -1 (691448, 0.758), 6.3 (1, 0.000), 6.5 (5, 0.000), 6.6 (11, 0.000), 6.7
## (46, 0.000), 6.8 (217, 0.000), 6.9 (690, 0.001), 7 (1738, 0.002), 7.1
## (4958, 0.005), 7.2 (16712, 0.018), 7.3 (62997, 0.069), 7.4 (96463, 0.106),
## 7.5 (33188, 0.036), 7.6 (3721, 0.004), 7.7 (291, 0.000), 7.8 (19, 0.000),
## 7.9 (2, 0.000), 8 (1, 0.000), 8.6 (1, 0.000)
## ---------------------------------------------------------------------------
## intubated_apache
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.393 141662 0.1552 0.2623
##
## ---------------------------------------------------------------------------
## wbc_apache
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 5611 0.988 9.145 8.983 -1.00 -1.00
## .25 .50 .75 .90 .95
## 3.60 8.50 13.40 18.90 23.28
##
## lowest : -1.00 0.01 0.02 0.03 0.04, highest: 196.80 197.00 197.70 199.00 199.20
## ---------------------------------------------------------------------------
## oobintubday1_apache
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.574 235413 0.258 0.3829
##
## ---------------------------------------------------------------------------
## oobventday1_apache
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.657 295615 0.324 0.438
##
## ---------------------------------------------------------------------------
## ventday1_apache
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.547 218677 0.2396 0.3644
##
## ---------------------------------------------------------------------------
## physicianspeciality
## n missing distinct
## 912509 0 49
##
## lowest : allergy/immunology anesthesiology anesthesiology/CCM cardiology critical care medicine (CCM)
## highest: surgery-transplant surgery-trauma surgery-vascular unknown urology
## ---------------------------------------------------------------------------
## acutephysiologyscore
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 198 1 43.81 25.13 16 20
## .25 .50 .75 .90 .95
## 27 38 54 76 92
##
## lowest : 0 1 2 3 4, highest: 194 195 198 200 206
## ---------------------------------------------------------------------------
## apachescore
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 212 1 55.54 27.83 23 28
## .25 .50 .75 .90 .95
## 37 51 68 90 106
##
## lowest : 1 2 3 4 5, highest: 208 209 211 214 230
## ---------------------------------------------------------------------------
## predictedicumortality
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 889923 1 0.05459 0.1406 0.002357 0.004004
## .25 .50 .75 .90 .95
## 0.009022 0.022689 0.064605 0.194698 0.368231
##
## lowest : -1.000000e+00 7.088864e-10 7.633918e-10 7.749529e-10 7.966238e-10
## highest: 9.831448e-01 9.833071e-01 9.851197e-01 9.859533e-01 9.951461e-01
## ---------------------------------------------------------------------------
## predictediculos
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 889227 1 3.851 2.513 1.135 1.555
## .25 .50 .75 .90 .95
## 2.184 3.319 5.192 7.244 8.309
##
## lowest : -1.0000000000 0.0005581499 0.0010462120 0.0033882155 0.0036456098
## highest: 15.2146312944 15.3433721860 15.3576234639 16.0262378684 19.9075117024
## ---------------------------------------------------------------------------
## predictedhospitalmortality
## n missing distinct Info Mean Gmd .05
## 912509 0 846588 1 0.04401 0.2669 -1.000000
## .10 .25 .50 .75 .90 .95
## 0.005689 0.017526 0.046130 0.122479 0.304494 0.494634
##
## lowest : -1.0000000000 0.0003451466 0.0003794773 0.0003825366 0.0004188721
## highest: 0.9930928093 0.9930994412 0.9932010502 0.9979823377 0.9981384119
## ---------------------------------------------------------------------------
## predictedhospitallos
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 846540 1 9.384 5.737 -1.000 3.711
## .25 .50 .75 .90 .95
## 6.308 9.053 12.161 15.609 18.401
##
## lowest : -1.000000e+00 9.883428e-04 3.367056e-03 9.694190e-03 1.226688e-02
## highest: 9.934482e+01 1.021803e+02 1.039875e+02 1.066029e+02 1.469374e+02
## ---------------------------------------------------------------------------
## preopmi
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.009 2663 0.002918 0.00582
##
## ---------------------------------------------------------------------------
## preopcardiaccath
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.023 6932 0.007597 0.01508
##
## ---------------------------------------------------------------------------
## ptcawithin24h
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.188 61222 0.06709 0.1252
##
## ---------------------------------------------------------------------------
## graftcount
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 10 0.04 2.999 0.03646 3 3
## .25 .50 .75 .90 .95
## 3 3 3 3 3
##
## Value 1 2 3 4 5 6 7 8 9
## Frequency 2419 3927 900090 4513 1288 227 34 9 1
## Proportion 0.003 0.004 0.986 0.005 0.001 0.000 0.000 0.000 0.000
##
## Value 10
## Frequency 1
## Proportion 0.000
## ---------------------------------------------------------------------------
## mbp_min
## n missing distinct Info Mean Gmd .05 .10
## 911199 1310 152 1 57.02 18.97 26 35
## .25 .50 .75 .90 .95
## 47 58 68 78 84
##
## lowest : 1 2 3 4 5, highest: 157 162 165 292 296
## ---------------------------------------------------------------------------
## sbp_min
## n missing distinct Info Mean Gmd .05 .10
## 911192 1317 172 1 58.88 18.98 29 37
## .25 .50 .75 .90 .95
## 49 59 70 80 86
##
## lowest : 1 2 3 4 5, highest: 174 175 176 177 179
## ---------------------------------------------------------------------------
## temperature_min
## n missing distinct Info Mean Gmd .05 .10
## 74236 838273 1881 1 40.71 14.61 23.9 30.7
## .25 .50 .75 .90 .95
## 34.8 36.1 36.9 80.3 97.0
##
## lowest : 0.05 0.10 0.20 0.25 0.30, highest: 105.20 105.60 106.00 108.40 109.70
## ---------------------------------------------------------------------------
## temperature_max
## n missing distinct Info Mean Gmd .05 .10
## 74236 838273 901 0.999 44.57 13.26 36.10 36.72
## .25 .50 .75 .90 .95
## 37.30 37.80 38.60 97.80 100.10
##
## lowest : 0.10 0.40 3.20 4.35 4.40, highest: 112.15 112.50 112.70 112.90 151.00
## ---------------------------------------------------------------------------
## heartrate_max
## n missing distinct Info Mean Gmd .05 .10
## 911360 1149 263 1 107.9 24.68 76 81
## .25 .50 .75 .90 .95
## 92 106 121 137 147
##
## lowest : 29 30 31 32 33, highest: 296 297 298 299 300
## ---------------------------------------------------------------------------
## respiratoryrate_max
## n missing distinct Info Mean Gmd .05 .10
## 864221 48288 208 0.998 33.09 13.66 20 22
## .25 .50 .75 .90 .95
## 24 29 36 47 57
##
## Value 0 500 13500 19000 27000 37000 51000 57500 58500
## Frequency 864212 1 1 1 1 1 1 1 1
## Proportion 1 0 0 0 0 0 0 0 0
##
## Value 63000
## Frequency 1
## Proportion 0
## ---------------------------------------------------------------------------
## heartrate_charted_max
## n missing distinct Info Mean Gmd .05 .10
## 829506 83003 272 1 102.4 24.91 70 76
## .25 .50 .75 .90 .95
## 87 100 116 132 142
##
## lowest : 5 7 14 15 18, highest: 320 347 360 361 379
## ---------------------------------------------------------------------------
## respiratoryrate_charted_max
## n missing distinct Info Mean Gmd .05 .10
## 834367 78142 79 0.998 27.72 9.502 17 19
## .25 .50 .75 .90 .95
## 22 26 31 39 46
##
## lowest : 1 2 3 4 5, highest: 75 76 77 78 79
## ---------------------------------------------------------------------------
## o2saturation_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 792701 119808 101 0.995 91.37 7.124 79 85
## .25 .50 .75 .90 .95
## 90 93 96 98 99
##
## lowest : 1 2 3 4 5, highest: 96 97 98 99 100
## ---------------------------------------------------------------------------
## nibp_systolic_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 808844 103665 268 1 97.44 23.54 65 72
## .25 .50 .75 .90 .95
## 84 96 110 124 134
##
## lowest : 1 2 3 4 5, highest: 246 248 256 261 269
## ---------------------------------------------------------------------------
## nibp_diastolic_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 809166 103343 195 0.999 49.74 15.58 27 33
## .25 .50 .75 .90 .95
## 41 49 58 67 74
##
## lowest : 1 2 3 4 5, highest: 185 187 188 190 226
## ---------------------------------------------------------------------------
## nibp_mean_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 767729 144780 195 1 64.52 17.6 40 46
## .25 .50 .75 .90 .95
## 54 63 74 85 92
##
## lowest : 0.13 0.61 0.74 0.87 1.00, highest: 194.00 195.00 196.00 200.00 232.00
## ---------------------------------------------------------------------------
## ibp_systolic_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 197536 714973 294 1 95.91 27.39 58 69
## .25 .50 .75 .90 .95
## 82 94 110 128 139
##
## lowest : 1 2 3 4 5, highest: 319 334 338 348 390
## ---------------------------------------------------------------------------
## ibp_diastolic_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 197464 715045 215 0.999 48.2 14.36 29 34
## .25 .50 .75 .90 .95
## 40 47 55 64 70
##
## lowest : 1 2 3 4 5, highest: 316 333 334 348 390
## ---------------------------------------------------------------------------
## ibp_mean_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 214633 697876 388 0.999 64.33 18.53 38 47
## .25 .50 .75 .90 .95
## 55 63 73 84 92
##
## lowest : 1 2 3 4 5, highest: 357 359 360 364 390
## ---------------------------------------------------------------------------
## mbp_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 814231 98278 265 1 63.45 17.71 39 45
## .25 .50 .75 .90 .95
## 54 63 73 84 91
##
## lowest : 0.13 0.61 0.74 0.87 1.00, highest: 194.00 196.00 200.00 232.00 287.00
## ---------------------------------------------------------------------------
## sbp_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 822995 89514 271 1 95.7 23.86 62 71
## .25 .50 .75 .90 .95
## 82 95 109 123 132
##
## lowest : 1 2 3 4 5, highest: 240 244 246 248 256
## ---------------------------------------------------------------------------
## temperature_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 893018 19491 684 0.996 36.27 0.7088 35.1 35.6
## .25 .50 .75 .90 .95
## 36.1 36.4 36.7 36.9 37.1
##
## lowest : 20.10 20.20 20.22 20.30 20.40, highest: 42.10 42.70 45.30 46.20 48.20
## ---------------------------------------------------------------------------
## temperature_charted_max
## n missing distinct Info Mean Gmd .05 .10
## 893018 19491 577 0.997 37.29 0.7655 36.40 36.60
## .25 .50 .75 .90 .95
## 36.90 37.16 37.60 38.20 38.70
##
## lowest : 21.70 27.90 28.10 28.80 28.88, highest: 48.33 48.60 48.70 48.80 48.90
## ---------------------------------------------------------------------------
## gcs_charted_min
## n missing distinct Info Mean Gmd .05 .10
## 619639 292870 14 0.878 12.4 3.671 3 6
## .25 .50 .75 .90 .95
## 10 14 15 15 15
##
## Value 3.0 4.0 5.0 6.0 7.0 8.0 9.0 10.0 11.0
## Frequency 43551 4164 3990 17521 21691 19150 18104 27352 21557
## Proportion 0.070 0.007 0.006 0.028 0.035 0.031 0.029 0.044 0.035
##
## Value 12.0 13.0 14.0 14.5 15.0
## Frequency 15589 33320 89442 1 304207
## Proportion 0.025 0.054 0.144 0.000 0.491
## ---------------------------------------------------------------------------
## bilirubin_max
## n missing distinct Info Mean Gmd .05 .10
## 377882 534627 1016 0.994 1.195 1.291 0.2 0.3
## .25 .50 .75 .90 .95
## 0.4 0.7 1.1 2.1 3.5
##
## lowest : 0.00 0.05 0.09 0.10 0.11, highest: 61.50 63.10 64.00 67.90 72.40
## ---------------------------------------------------------------------------
## creatinine_max
## n missing distinct Info Mean Gmd .05 .10
## 823925 88584 2539 1 1.547 1.279 0.51 0.60
## .25 .50 .75 .90 .95
## 0.76 1.00 1.57 2.95 4.60
##
## lowest : 0.00 0.06 0.07 0.10 0.11, highest: 48.59 50.70 51.70 56.00 107.00
## ---------------------------------------------------------------------------
## lactate_min
## n missing distinct Info Mean Gmd .05 .10
## 214669 697840 1105 0.999 2.107 1.778 0.6 0.7
## .25 .50 .75 .90 .95
## 1.0 1.5 2.3 3.8 5.9
##
## lowest : 0.00 0.10 0.11 0.20 0.24, highest: 36.90 38.50 38.90 39.73 40.90
## ---------------------------------------------------------------------------
## lactate_max
## n missing distinct Info Mean Gmd .05 .10
## 214669 697840 1550 0.999 2.909 2.698 0.7 0.8
## .25 .50 .75 .90 .95
## 1.2 1.8 3.2 6.1 9.2
##
## Value 0 5 10 15 20 25 30 35 40
## Frequency 141487 57611 9968 3630 1381 419 128 31 8
## Proportion 0.659 0.268 0.046 0.017 0.006 0.002 0.001 0.000 0.000
##
## Value 45 510
## Frequency 5 1
## Proportion 0.000 0.000
## ---------------------------------------------------------------------------
## pao2_min
## n missing distinct Info Mean Gmd .05 .10
## 346221 566288 3508 1 101.6 57.56 44 54
## .25 .50 .75 .90 .95
## 66 83 115 166 216
##
## Value 0 100 200 300 400 500 600 700 1000
## Frequency 27177 273711 33100 7093 3447 1448 233 7 2
## Proportion 0.078 0.791 0.096 0.020 0.010 0.004 0.001 0.000 0.000
##
## Value 1100 2800 11800
## Frequency 1 1 1
## Proportion 0.000 0.000 0.000
## ---------------------------------------------------------------------------
## pao2_max
## n missing distinct Info Mean Gmd .05 .10
## 346221 566288 4902 1 165.3 113 61.9 69.2
## .25 .50 .75 .90 .95
## 87.0 125.0 206.0 335.0 413.0
##
## 0 (5543, 0.016), 100 (202735, 0.586), 200 (75124, 0.217), 300 (31943,
## 0.092), 400 (19609, 0.057), 500 (9384, 0.027), 600 (1778, 0.005), 700 (85,
## 0.000), 800 (8, 0.000), 900 (1, 0.000), 1000 (2, 0.000), 1100 (2, 0.000),
## 1200 (1, 0.000), 1700 (1, 0.000), 2100 (1, 0.000), 2800 (1, 0.000), 3600
## (1, 0.000), 5400 (1, 0.000), 11800 (1, 0.000)
## ---------------------------------------------------------------------------
## paco2_min
## n missing distinct Info Mean Gmd .05 .10
## 346097 566412 1146 1 38.87 12.46 23.3 26.7
## .25 .50 .75 .90 .95
## 31.7 37.0 43.7 53.0 61.2
##
## Value -100 0 50 100 150 200 250 300 400
## Frequency 1 23031 317541 5413 90 9 2 1 2
## Proportion 0.000 0.067 0.917 0.016 0.000 0.000 0.000 0.000 0.000
##
## Value 450 3650 4550
## Frequency 5 1 1
## Proportion 0.000 0.000 0.000
## ---------------------------------------------------------------------------
## paco2_max
## n missing distinct Info Mean Gmd .05 .10
## 346097 566412 1487 1 46.07 16.28 27.4 31.0
## .25 .50 .75 .90 .95
## 36.0 43.0 51.0 65.0 78.0
##
## Value 0 100 200 300 400 500 600 700 3600
## Frequency 253905 91948 216 7 10 5 2 1 1
## Proportion 0.734 0.266 0.001 0.000 0.000 0.000 0.000 0.000 0.000
##
## Value 4600 7500
## Frequency 1 1
## Proportion 0.000 0.000
## ---------------------------------------------------------------------------
## platelet_min
## n missing distinct Info Mean Gmd .05 .10
## 791142 121367 1099 1 197.2 99.31 68 94
## .25 .50 .75 .90 .95
## 137 186 243 308 361
##
## lowest : 0.00 1.00 1.05 2.00 3.00
## highest: 2113.00 2221.00 2353.00 2371.00 2449.00
## ---------------------------------------------------------------------------
## inr_max
## n missing distinct Info Mean Gmd .05 .10
## 364715 547794 1085 0.993 1.614 0.815 1.00 1.00
## .25 .50 .75 .90 .95
## 1.10 1.30 1.60 2.50 3.45
##
## lowest : 0.00 0.50 0.60 0.66 0.70, highest: 24.50 27.20 32.10 38.10 130.00
## ---------------------------------------------------------------------------
## wbc_min
## n missing distinct Info Mean Gmd .05 .10
## 794580 117929 5349 1 11.29 6.364 4.3 5.4
## .25 .50 .75 .90 .95
## 7.3 9.9 13.5 18.1 22.1
##
## lowest : 0.00 0.01 0.02 0.03 0.04, highest: 613.40 774.00 776.40 778.40 813.90
## ---------------------------------------------------------------------------
## wbc_max
## n missing distinct Info Mean Gmd .05 .10
## 794580 117929 5938 1 12.52 7.252 4.7 5.8
## .25 .50 .75 .90 .95
## 7.9 10.9 15.0 20.5 25.0
##
## lowest : 0.00 0.01 0.02 0.03 0.04, highest: 657.46 774.00 776.40 778.40 813.90
## ---------------------------------------------------------------------------
## ptt_max
## n missing distinct Info Mean Gmd .05 .10
## 266885 645624 2321 1 44.02 24.64 24.0 25.4
## .25 .50 .75 .90 .95
## 28.5 33.9 45.1 77.1 107.0
##
## lowest : 12.2 14.2 14.5 15.0 15.1, highest: 296.3 296.9 298.5 300.0 380.0
## ---------------------------------------------------------------------------
## bands_max
## n missing distinct Info Mean Gmd .05 .10
## 76228 836281 737 0.997 12.54 13.61 1 1
## .25 .50 .75 .90 .95
## 3 8 17 31 40
##
## Value 0 50 100 6400
## Frequency 65175 10762 290 1
## Proportion 0.855 0.141 0.004 0.000
## ---------------------------------------------------------------------------
## ph_min
## n missing distinct Info Mean Gmd .05 .10
## 335524 576985 1028 1 7.375 0.2206 7.110 7.180
## .25 .50 .75 .90 .95
## 7.271 7.341 7.401 7.450 7.480
##
## Value 0 100 700 7200 7300
## Frequency 335518 2 2 1 1
## Proportion 1 0 0 0 0
## ---------------------------------------------------------------------------
## basedeficit_min
## n missing distinct Info Mean Gmd .05 .10
## 59048 853461 429 0.999 6.095 5.381 0.7 1.0
## .25 .50 .75 .90 .95
## 2.5 4.9 8.0 13.0 17.0
##
## lowest : -30.0 -24.4 -23.9 -21.0 -18.2, highest: 34.3 34.4 34.7 35.0 36.6
## ---------------------------------------------------------------------------
## basedeficit_max
## n missing distinct Info Mean Gmd .05 .10
## 59048 853461 429 0.999 6.095 5.381 0.7 1.0
## .25 .50 .75 .90 .95
## 2.5 4.9 8.0 13.0 17.0
##
## lowest : -30.0 -24.4 -23.9 -21.0 -18.2, highest: 34.3 34.4 34.7 35.0 36.6
## ---------------------------------------------------------------------------
## ast_max
## n missing distinct Info Mean Gmd .05 .10
## 383902 528607 6246 1 178.8 291.4 12 15
## .25 .50 .75 .90 .95
## 20 32 69 198 467
##
## lowest : 0 1 2 3 4, highest: 43957 46817 54043 56238 200111
## ---------------------------------------------------------------------------
## alt_max
## n missing distinct Info Mean Gmd .05 .10
## 378856 533653 4501 1 109 166.2 10 12
## .25 .50 .75 .90 .95
## 17 28 51 128 299
##
## lowest : 0 1 2 3 4, highest: 16185 16738 17091 18200 18978
## ---------------------------------------------------------------------------
## alp_max
## n missing distinct Info Mean Gmd .05 .10
## 371564 540945 1430 1 101.2 68.55 39 46
## .25 .50 .75 .90 .95
## 59 78 110 165 228
##
## lowest : -154.0 1.0 2.0 3.0 3.7
## highest: 4254.0 4956.0 7443.0 8146.0 10001.0
## ---------------------------------------------------------------------------
## penicilin
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.016 4748 0.005255 0.01046
##
## ---------------------------------------------------------------------------
## penicilin_anti_staph
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.003 1015 0.001123 0.002244
##
## ---------------------------------------------------------------------------
## penicilin_anti_pseudo
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.352 122743 0.1359 0.2348
##
## ---------------------------------------------------------------------------
## augmentin_unasyn
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.036 10897 0.01206 0.02383
##
## ---------------------------------------------------------------------------
## cephalosporin_1st_gen
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.132 41557 0.046 0.08776
##
## ---------------------------------------------------------------------------
## cephalosporin_2nd_gen
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.077 23685 0.02621 0.05106
##
## ---------------------------------------------------------------------------
## cephalosporin_3rd_gen
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.209 68100 0.07537 0.1394
##
## ---------------------------------------------------------------------------
## cephalosporin_4th_5th_gen
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.094 29182 0.0323 0.06251
##
## ---------------------------------------------------------------------------
## carbapenems
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.086 26826 0.02969 0.05762
##
## ---------------------------------------------------------------------------
## monobactam
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.034 10318 0.01142 0.02258
##
## ---------------------------------------------------------------------------
## fq
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.253 84164 0.09315 0.169
##
## ---------------------------------------------------------------------------
## vancomycin
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.464 173027 0.1915 0.3097
##
## ---------------------------------------------------------------------------
## amg
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.044 13504 0.01495 0.02945
##
## ---------------------------------------------------------------------------
## polymixins
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.003 769 0.0008511 0.001701
##
## ---------------------------------------------------------------------------
## linezolid
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.024 7163 0.007928 0.01573
##
## ---------------------------------------------------------------------------
## dapto
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.01 3080 0.003409 0.006795
##
## ---------------------------------------------------------------------------
## clinda
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.051 15696 0.01737 0.03414
##
## ---------------------------------------------------------------------------
## doxycyclin
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.023 7049 0.007802 0.01548
##
## ---------------------------------------------------------------------------
## macrolides
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.115 36029 0.03988 0.07657
##
## ---------------------------------------------------------------------------
## sulfa
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.025 7480 0.008279 0.01642
##
## ---------------------------------------------------------------------------
## metronidazole
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.132 41517 0.04595 0.08768
##
## ---------------------------------------------------------------------------
## nitrofurantoin
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.004 1250 0.001384 0.002763
##
## ---------------------------------------------------------------------------
## tigecycline
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.007 2127 0.002354 0.004697
##
## ---------------------------------------------------------------------------
## ceftriaxone
## n missing distinct Info Mean Gmd
## 903501 9008 1 0 0 0
##
## Value 0
## Frequency 903501
## Proportion 1
## ---------------------------------------------------------------------------
## cefotaxime
## n missing distinct Info Mean Gmd
## 903501 9008 1 0 0 0
##
## Value 0
## Frequency 903501
## Proportion 1
## ---------------------------------------------------------------------------
## ampicillin_sulbactam
## n missing distinct Info Mean Gmd
## 903501 9008 1 0 0 0
##
## Value 0
## Frequency 903501
## Proportion 1
## ---------------------------------------------------------------------------
## levofloxacin
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.033 9936 0.011 0.02175
##
## ---------------------------------------------------------------------------
## moxifloxacin
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.004 1097 0.001214 0.002425
##
## ---------------------------------------------------------------------------
## piperacillin_tazobactam
## n missing distinct Info Mean Gmd
## 903501 9008 1 0 0 0
##
## Value 0
## Frequency 903501
## Proportion 1
## ---------------------------------------------------------------------------
## cefepim
## n missing distinct Info Mean Gmd
## 903501 9008 1 0 0 0
##
## Value 0
## Frequency 903501
## Proportion 1
## ---------------------------------------------------------------------------
## meropenem
## n missing distinct Info Mean Gmd
## 903501 9008 1 0 0 0
##
## Value 0
## Frequency 903501
## Proportion 1
## ---------------------------------------------------------------------------
## imipenem
## n missing distinct Info Mean Gmd
## 903501 9008 1 0 0 0
##
## Value 0
## Frequency 903501
## Proportion 1
## ---------------------------------------------------------------------------
## doripenem
## n missing distinct Info Mean Gmd
## 903501 9008 1 0 0 0
##
## Value 0
## Frequency 903501
## Proportion 1
## ---------------------------------------------------------------------------
## gentamicin
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0 22 2.435e-05 4.87e-05
##
## ---------------------------------------------------------------------------
## tobramycin
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.001 172 0.0001904 0.0003807
##
## ---------------------------------------------------------------------------
## amikacin
## n missing distinct Info Mean Gmd
## 903501 9008 1 0 0 0
##
## Value 0
## Frequency 903501
## Proportion 1
## ---------------------------------------------------------------------------
## dopamine_infusion
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.076 23820 0.0261 0.05084
##
## ---------------------------------------------------------------------------
## epinephrine_infusion
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.032 9938 0.01089 0.02154
##
## ---------------------------------------------------------------------------
## norepinephrine_infusion
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.234 77890 0.08536 0.1561
##
## ---------------------------------------------------------------------------
## phenylephrine_infusion
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.083 26080 0.02858 0.05553
##
## ---------------------------------------------------------------------------
## vasopressin_infusion
## n missing distinct Info Sum Mean Gmd
## 347509 565000 2 0.132 16059 0.04621 0.08815
##
## ---------------------------------------------------------------------------
## milrinone_infusion
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.019 5782 0.006336 0.01259
##
## ---------------------------------------------------------------------------
## heparin_infusion
## n missing distinct Info Sum Mean Gmd
## 347509 565000 2 0.303 39684 0.1142 0.2023
##
## ---------------------------------------------------------------------------
## dopamine_medication
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.142 45389 0.04974 0.09453
##
## ---------------------------------------------------------------------------
## epinephrine_medication
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.101 31830 0.03488 0.06733
##
## ---------------------------------------------------------------------------
## norepinephrine_medication
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.314 108457 0.1189 0.2095
##
## ---------------------------------------------------------------------------
## phenylephrine_medication
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.165 53473 0.0586 0.1103
##
## ---------------------------------------------------------------------------
## vasopressin_medication
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.097 30270 0.0335 0.06476
##
## ---------------------------------------------------------------------------
## milrinone_medication
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.03 9190 0.01007 0.01994
##
## ---------------------------------------------------------------------------
## heparin_medication
## n missing distinct Info Sum Mean Gmd
## 903501 9008 2 0.581 237112 0.2624 0.3871
##
## ---------------------------------------------------------------------------
## sepsis
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.318 109798 0.1203 0.2117
##
## ---------------------------------------------------------------------------
## sepsis_priority
## n missing distinct Info Mean Gmd
## 912509 0 4 0.319 0.1965 0.3579
##
## Value 0 1 2 3
## Frequency 802711 66404 17251 26143
## Proportion 0.880 0.073 0.019 0.029
## ---------------------------------------------------------------------------
## infection
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.597 250420 0.2744 0.3982
##
## ---------------------------------------------------------------------------
## infection_priority
## n missing distinct Info Mean Gmd
## 912509 0 4 0.615 0.495 0.7861
##
## Value 0 1 2 3
## Frequency 662089 118863 61871 69686
## Proportion 0.726 0.130 0.068 0.076
## ---------------------------------------------------------------------------
## aidshiv
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.01 2961 0.003245 0.006469
##
## ---------------------------------------------------------------------------
## aidshiv_priority
## n missing distinct Info Mean Gmd
## 912509 0 4 0.01 0.007939 0.01583
##
## Value 0 1 2 3
## Frequency 909548 48 1543 1370
## Proportion 0.997 0.000 0.002 0.002
## ---------------------------------------------------------------------------
## organfailure
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.725 372946 0.4087 0.4833
##
## ---------------------------------------------------------------------------
## organfailure_priority
## n missing distinct Info Mean Gmd
## 912509 0 4 0.785 0.7615 1.051
##
## Value 0 1 2 3
## Frequency 539563 159065 105867 108014
## Proportion 0.591 0.174 0.116 0.118
## ---------------------------------------------------------------------------
## altered_mental_status
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.261 87685 0.09609 0.1737
##
## ---------------------------------------------------------------------------
## altered_mental_status_priority
## n missing distinct Info Mean Gmd
## 912509 0 4 0.261 0.2117 0.3901
##
## Value 0 1 2 3
## Frequency 824824 16981 35888 34816
## Proportion 0.904 0.019 0.039 0.038
## ---------------------------------------------------------------------------
## infection_apache
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.416 151832 0.1664 0.2774
##
## ---------------------------------------------------------------------------
## organfailure_apache
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.176 57210 0.0627 0.1175
##
## ---------------------------------------------------------------------------
## prompt_inflam
## n missing distinct Info Sum Mean Gmd
## 380100 532409 2 0.568 96341 0.2535 0.3784
##
## ---------------------------------------------------------------------------
## prompt_severe_sepsis
## n missing distinct Info Sum Mean Gmd
## 380100 532409 2 0.254 35505 0.09341 0.1694
##
## ---------------------------------------------------------------------------
## prompt_sepsis
## n missing distinct Info Sum Mean Gmd
## 380100 532409 2 0.12 15907 0.04185 0.0802
##
## ---------------------------------------------------------------------------
## prompt_inflam_with_org_dys
## n missing distinct Info Sum Mean Gmd
## 380100 532409 2 0 4 1.052e-05 2.105e-05
##
## ---------------------------------------------------------------------------
## prompt_clinical_respone_req
## n missing distinct Info Sum Mean Gmd
## 380100 532409 2 0.004 379551 0.9986 0.002885
##
## ---------------------------------------------------------------------------
## sofa_respiration
## n missing distinct Info Mean Gmd
## 912509 0 5 0.386 0.3666 0.6443
##
## Value 0 1 2 3 4
## Frequency 775552 17318 59473 42413 17753
## Proportion 0.850 0.019 0.065 0.046 0.019
## ---------------------------------------------------------------------------
## sofa_coagulation
## n missing distinct Info Mean Gmd
## 912509 0 5 0.603 0.3963 0.6278
##
## Value 0 1 2 3 4
## Frequency 667848 153552 69848 16638 4623
## Proportion 0.732 0.168 0.077 0.018 0.005
## ---------------------------------------------------------------------------
## sofa_liver
## n missing distinct Info Mean Gmd
## 912509 0 5 0.261 0.155 0.2872
##
## Value 0 1 2 3 4
## Frequency 824760 46708 31852 5737 3452
## Proportion 0.904 0.051 0.035 0.006 0.004
## ---------------------------------------------------------------------------
## sofa_cardiovascular
## n missing distinct Info Mean Gmd
## 912509 0 3 0.778 1.185 0.97
##
## Value 0 1 3
## Frequency 193336 538176 180997
## Proportion 0.212 0.590 0.198
## ---------------------------------------------------------------------------
## sofa_cns
## n missing distinct Info Mean Gmd
## 912509 0 5 0.794 0.8861 1.246
##
## Value 0 1 2 3 4
## Frequency 533497 152624 82389 84845 59154
## Proportion 0.585 0.167 0.090 0.093 0.065
## ---------------------------------------------------------------------------
## sofa_renal
## n missing distinct Info Mean Gmd
## 912509 0 5 0.759 0.7813 1.143
##
## Value 0 1 2 3 4
## Frequency 562276 163728 70095 56639 59771
## Proportion 0.616 0.179 0.077 0.062 0.066
## ---------------------------------------------------------------------------
## sofa_renal_baseline
## n missing distinct Info Mean Gmd
## 912509 0 2 0.097 0.1343 0.2596
##
## Value 0 4
## Frequency 881875 30634
## Proportion 0.966 0.034
## ---------------------------------------------------------------------------
## sofa_liver_baseline
## n missing distinct Info Mean Gmd
## 912509 0 2 0.061 0.08357 0.1637
##
## Value 0 4
## Frequency 893444 19065
## Proportion 0.979 0.021
## ---------------------------------------------------------------------------
## sofa_respiration_baseline
## n missing distinct Info Mean Gmd
## 912509 0 2 0.549 0.4819 0.7315
##
## Value 0 2
## Frequency 692652 219857
## Proportion 0.759 0.241
## ---------------------------------------------------------------------------
## cardiovascular_baseline
## n missing distinct
## 912509 0 2
##
## Value 0 1
## Frequency 705303 207206
## Proportion 0.773 0.227
## ---------------------------------------------------------------------------
## soi_alpha
## n missing distinct Info Mean Gmd .05 .10
## 614401 298108 468 0.999 2.997 0.536 2.50 2.52
## .25 .50 .75 .90 .95
## 2.60 2.83 3.17 3.74 4.03
##
## lowest : 2.50 2.51 2.52 2.53 2.54, highest: 7.60 7.61 7.88 7.94 8.00
## ---------------------------------------------------------------------------
## soi_minutes
## n missing distinct Info Mean Gmd .05 .10
## 614401 298108 301 0.994 176.2 300.6 -60 -60
## .25 .50 .75 .90 .95
## -5 30 215 695 965
##
## lowest : -60 -55 -50 -45 -40, highest: 1420 1425 1430 1435 1440
## ---------------------------------------------------------------------------
## od_alpha
## n missing distinct Info Mean Gmd
## 760467 152042 7 0.352 1.173 0.3065
##
## Value 1 2 3 4 5 6 7
## Frequency 657571 79763 18657 3839 572 63 2
## Proportion 0.865 0.105 0.025 0.005 0.001 0.000 0.000
## ---------------------------------------------------------------------------
## od_minutes
## n missing distinct Info Mean Gmd .05 .10
## 760467 152042 301 0.961 149.8 291.5 -60 -60
## .25 .50 .75 .90 .95
## -60 15 200 625 910
##
## lowest : -60 -55 -50 -45 -40, highest: 1420 1425 1430 1435 1440
## ---------------------------------------------------------------------------
## both_soi_alpha
## n missing distinct Info Mean Gmd .05 .10
## 502508 410001 482 0.999 3.111 0.636 2.50 2.53
## .25 .50 .75 .90 .95
## 2.65 2.95 3.35 4.00 4.37
##
## lowest : 2.50 2.51 2.52 2.53 2.54, highest: 7.83 7.88 7.94 8.00 9.00
## ---------------------------------------------------------------------------
## both_od_alpha
## n missing distinct Info Mean Gmd
## 502508 410001 7 0.675 1.45 0.672
##
## Value 1 2 3 4 5 6 7
## Frequency 341634 109399 39914 9748 1662 147 4
## Proportion 0.680 0.218 0.079 0.019 0.003 0.000 0.000
## ---------------------------------------------------------------------------
## both_minutes
## n missing distinct Info Mean Gmd .05 .10
## 502508 410001 301 0.996 225.9 347.6 -60 -60
## .25 .50 .75 .90 .95
## 0 65 330 815 1055
##
## lowest : -60 -55 -50 -45 -40, highest: 1420 1425 1430 1435 1440
## ---------------------------------------------------------------------------
## soi_alteredmentalstatus
## n missing distinct Info Sum Mean Gmd
## 614401 298108 2 0.148 32028 0.05213 0.09882
##
## ---------------------------------------------------------------------------
## soi_glucose
## n missing distinct Info Mean Gmd .05 .10
## 614401 298108 121 0.873 0.5743 0.4798 0.0 0.0
## .25 .50 .75 .90 .95
## 0.0 0.8 1.0 1.0 1.0
##
## lowest : 0.00000000 0.01000000 0.02000000 0.03000000 0.03333333
## highest: 0.96666667 0.97000000 0.98000000 0.99000000 1.00000000
## ---------------------------------------------------------------------------
## soi_heartrate
## n missing distinct Info Mean Gmd .05 .10
## 614401 298108 21 0.896 0.6629 0.4226 0.0 0.0
## .25 .50 .75 .90 .95
## 0.3 0.9 1.0 1.0 1.0
##
## lowest : 0.00 0.05 0.10 0.15 0.20, highest: 0.80 0.85 0.90 0.95 1.00
## ---------------------------------------------------------------------------
## soi_inr
## n missing distinct Info Mean Gmd .05 .10
## 614401 298108 61 0.57 0.1606 0.2655 0 0
## .25 .50 .75 .90 .95
## 0 0 0 1 1
##
## lowest : 0.00000000 0.01666667 0.03333333 0.05000000 0.06666667
## highest: 0.93333333 0.95000000 0.96666667 0.98333333 1.00000000
## ---------------------------------------------------------------------------
## soi_respiratoryrate
## n missing distinct Info Mean Gmd .05 .10
## 614401 298108 53 0.956 0.661 0.3808 0.0000 0.0000
## .25 .50 .75 .90 .95
## 0.4167 0.7500 1.0000 1.0000 1.0000
##
## lowest : 0.000000000 0.008333333 0.027777778 0.041666667 0.083333333
## highest: 0.944444444 0.958333333 0.972222222 0.983333333 1.000000000
## ---------------------------------------------------------------------------
## soi_temperature
## n missing distinct Info Mean Gmd .05 .10
## 614401 298108 257 0.724 0.1621 0.2557 0.0 0.0
## .25 .50 .75 .90 .95
## 0.0 0.0 0.2 0.7 1.0
##
## lowest : 0.000000000 0.001764706 0.016470588 0.029411765 0.032679739
## highest: 0.980588235 0.982235294 0.982352941 0.997160000 1.000000000
## ---------------------------------------------------------------------------
## soi_bands
## n missing distinct Info Mean Gmd .05 .10
## 614401 298108 188 0.168 0.04862 0.09242 0.0 0.0
## .25 .50 .75 .90 .95
## 0.0 0.0 0.0 0.0 0.5
##
## lowest : 0.00000000 0.00500000 0.01666667 0.01833333 0.02833333
## highest: 0.95166667 0.96000000 0.96666667 0.98333333 1.00000000
## ---------------------------------------------------------------------------
## soi_wbc
## n missing distinct Info Mean Gmd .05 .10
## 614401 298108 601 0.943 0.5307 0.4695 0.0000 0.0000
## .25 .50 .75 .90 .95
## 0.0000 0.5667 1.0000 1.0000 1.0000
##
## lowest : 0.000000000 0.001666667 0.003333333 0.005000000 0.006666667
## highest: 0.993333333 0.995000000 0.996666667 0.998333333 1.000000000
## ---------------------------------------------------------------------------
## soi_lactate
## n missing distinct Info Sum Mean Gmd
## 614401 298108 2 0.371 88766 0.1445 0.2472
##
## ---------------------------------------------------------------------------
## od_liver
## n missing distinct Info Sum Mean Gmd
## 760467 152042 2 0.294 83849 0.1103 0.1962
##
## ---------------------------------------------------------------------------
## od_cardiovascular
## n missing distinct Info Sum Mean Gmd
## 760467 152042 2 0.74 423395 0.5568 0.4936
##
## ---------------------------------------------------------------------------
## od_respiratory
## n missing distinct Info Sum Mean Gmd
## 760467 152042 2 0.416 126479 0.1663 0.2773
##
## ---------------------------------------------------------------------------
## od_kidney
## n missing distinct Info Sum Mean Gmd
## 760467 152042 2 0.214 58932 0.07749 0.143
##
## ---------------------------------------------------------------------------
## od_lactate
## n missing distinct Info Sum Mean Gmd
## 760467 152042 2 0.296 84365 0.1109 0.1973
##
## ---------------------------------------------------------------------------
## od_metabolic
## n missing distinct Info Sum Mean Gmd
## 760467 152042 2 0.371 110108 0.1448 0.2477
##
## ---------------------------------------------------------------------------
## od_hematologic
## n missing distinct Info Sum Mean Gmd
## 760467 152042 2 0.018 4548 0.005981 0.01189
##
## ---------------------------------------------------------------------------
## both_soi_alteredmentalstatus
## n missing distinct Info Sum Mean Gmd
## 502508 410001 2 0.131 22935 0.04564 0.08712
##
## ---------------------------------------------------------------------------
## both_soi_glucose
## n missing distinct Info Mean Gmd .05 .10
## 502508 410001 121 0.87 0.5656 0.4832 0.0 0.0
## .25 .50 .75 .90 .95
## 0.0 0.8 1.0 1.0 1.0
##
## lowest : 0.00000000 0.01000000 0.02000000 0.03000000 0.03333333
## highest: 0.96666667 0.97000000 0.98000000 0.99000000 1.00000000
## ---------------------------------------------------------------------------
## both_soi_heartrate
## n missing distinct Info Mean Gmd .05 .10
## 502508 410001 21 0.884 0.6666 0.4229 0.0 0.0
## .25 .50 .75 .90 .95
## 0.3 0.9 1.0 1.0 1.0
##
## lowest : 0.00 0.05 0.10 0.15 0.20, highest: 0.80 0.85 0.90 0.95 1.00
## ---------------------------------------------------------------------------
## both_soi_inr
## n missing distinct Info Mean Gmd .05 .10
## 502508 410001 61 0.624 0.1812 0.2912 0.0000 0.0000
## .25 .50 .75 .90 .95
## 0.0000 0.0000 0.1667 1.0000 1.0000
##
## lowest : 0.00000000 0.01666667 0.03333333 0.05000000 0.06666667
## highest: 0.93333333 0.95000000 0.96666667 0.98333333 1.00000000
## ---------------------------------------------------------------------------
## both_soi_respiratoryrate
## n missing distinct Info Mean Gmd .05 .10
## 502508 410001 51 0.949 0.6678 0.3831 0.0000 0.0000
## .25 .50 .75 .90 .95
## 0.4167 0.7500 1.0000 1.0000 1.0000
##
## lowest : 0.000000000 0.008333333 0.027777778 0.041666667 0.055555556
## highest: 0.933333333 0.944444444 0.958333333 0.972222222 1.000000000
## ---------------------------------------------------------------------------
## both_soi_temperature
## n missing distinct Info Mean Gmd .05 .10
## 502508 410001 258 0.744 0.172 0.2677 0.0 0.0
## .25 .50 .75 .90 .95
## 0.0 0.0 0.2 0.7 1.0
##
## lowest : 0.000000000 0.001764706 0.029411765 0.032679739 0.032941176
## highest: 0.980588235 0.982235294 0.982352941 0.997160000 1.000000000
## ---------------------------------------------------------------------------
## both_soi_bands
## n missing distinct Info Mean Gmd .05 .10
## 502508 410001 168 0.194 0.05737 0.108 0.0000 0.0000
## .25 .50 .75 .90 .95
## 0.0000 0.0000 0.0000 0.0000 0.8333
##
## lowest : 0.000000000 0.008333333 0.016666667 0.018333333 0.028333333
## highest: 0.953333333 0.960000000 0.966666667 0.983333333 1.000000000
## ---------------------------------------------------------------------------
## both_soi_wbc
## n missing distinct Info Mean Gmd .05 .10
## 502508 410001 601 0.936 0.5657 0.464 0.00000 0.00000
## .25 .50 .75 .90 .95
## 0.02333 0.65833 1.00000 1.00000 1.00000
##
## lowest : 0.000000000 0.001666667 0.003333333 0.005000000 0.006666667
## highest: 0.993333333 0.995000000 0.996666667 0.998333333 1.000000000
## ---------------------------------------------------------------------------
## both_soi_lactate
## n missing distinct Info Sum Mean Gmd
## 502508 410001 2 0.459 94798 0.1886 0.3061
##
## ---------------------------------------------------------------------------
## both_od_liver
## n missing distinct Info Sum Mean Gmd
## 502508 410001 2 0.41 81993 0.1632 0.2731
##
## ---------------------------------------------------------------------------
## both_od_cardiovascular
## n missing distinct Info Sum Mean Gmd
## 502508 410001 2 0.745 271953 0.5412 0.4966
##
## ---------------------------------------------------------------------------
## both_od_respiratory
## n missing distinct Info Sum Mean Gmd
## 502508 410001 2 0.556 123498 0.2458 0.3707
##
## ---------------------------------------------------------------------------
## both_od_kidney
## n missing distinct Info Sum Mean Gmd
## 502508 410001 2 0.234 42853 0.08528 0.156
##
## ---------------------------------------------------------------------------
## both_od_lactate
## n missing distinct Info Sum Mean Gmd
## 502508 410001 2 0.459 94798 0.1886 0.3061
##
## ---------------------------------------------------------------------------
## both_od_metabolic
## n missing distinct Info Sum Mean Gmd
## 502508 410001 2 0.506 107853 0.2146 0.3371
##
## ---------------------------------------------------------------------------
## both_od_hematologic
## n missing distinct Info Sum Mean Gmd
## 502508 410001 2 0.032 5438 0.01082 0.02141
##
## ---------------------------------------------------------------------------
## patientweight
## n missing distinct Info Mean Gmd .05 .10
## 898761 13748 13119 1 83.7 27.75 49.80 55.30
## .25 .50 .75 .90 .95
## 66.00 80.00 96.71 115.67 130.00
##
## lowest : 0.00 0.09 0.27 0.40 0.50, highest: 909.90 949.00 953.00 956.00 969.00
## ---------------------------------------------------------------------------
## BMI
## n missing distinct Info Mean Gmd .05 .10
## 882077 30432 184910 1 Inf NaN 18.50 20.29
## .25 .50 .75 .90 .95
## 23.47 27.55 32.87 39.52 44.84
##
## lowest : 0.000000e+00 1.020408e-02 1.937504e-02 2.547485e-02 1.132216e-01
## highest: 1.352158e+06 1.504164e+06 1.598657e+06 1.999887e+06 Inf
## ---------------------------------------------------------------------------
## BMI_Ranges
## n missing distinct
## 912509 0 5
##
## Value (0,18.5] (18.5,25] (25,35] (35,200]
## Frequency 44009 257638 416522 162054
## Proportion 0.048 0.282 0.456 0.178
##
## Value Other/Unknown
## Frequency 32286
## Proportion 0.035
## ---------------------------------------------------------------------------
## age_Ranges
## n missing distinct
## 912509 0 8
##
## Value (0,25] (25,35] (35,45] (45,55] (55,65] (65,75] (75,85]
## Frequency 30083 45906 67771 136077 191660 200706 165443
## Proportion 0.033 0.050 0.074 0.149 0.210 0.220 0.181
##
## Value (85,100]
## Frequency 74863
## Proportion 0.082
## ---------------------------------------------------------------------------
## hospitalLOS_Ranges
## n missing distinct
## 912506 3 10
##
## Value (0,1] (1,3] (3,5] (5,10] (10,20] (20,30]
## Frequency 42243 201490 185718 274367 152013 36187
## Proportion 0.046 0.221 0.204 0.301 0.167 0.040
##
## Value (30,60] (60,90] (90,150] (150,999]
## Frequency 17656 1914 710 208
## Proportion 0.019 0.002 0.001 0.000
## ---------------------------------------------------------------------------
## icuLOS_Ranges
## n missing distinct
## 912509 0 8
##
## Value (0,1] (1,3] (3,5] (5,10] (10,20] (20,30] (30,60]
## Frequency 222500 426937 128031 89011 36285 7092 2475
## Proportion 0.244 0.468 0.140 0.098 0.040 0.008 0.003
##
## Value (60,999]
## Frequency 178
## Proportion 0.000
## ---------------------------------------------------------------------------
## ethnicity2
## n missing distinct
## 912509 0 6
##
## Value Caucasian African American Hispanic
## Frequency 695367 105292 41393
## Proportion 0.762 0.115 0.045
##
## Value Asian Native American Other/Unknown
## Frequency 11695 6765 51997
## Proportion 0.013 0.007 0.057
## ---------------------------------------------------------------------------
## gender2
## n missing distinct
## 912509 0 3
##
## Value Male Female Other/Unknown
## Frequency 490533 421748 228
## Proportion 0.538 0.462 0.000
## ---------------------------------------------------------------------------
## hospital_region2
## n missing distinct
## 912509 0 5
##
## Value Midwest Northeast South West Unknown
## Frequency 383075 73523 283987 116783 55141
## Proportion 0.420 0.081 0.311 0.128 0.060
## ---------------------------------------------------------------------------
## sepsis_outcome
## n missing distinct
## 912509 0 2
##
## Value FALSE TRUE
## Frequency 725639 186870
## Proportion 0.795 0.205
## ---------------------------------------------------------------------------
## group
## n missing distinct
## 912509 0 12
##
## Cardiovascular (295348, 0.324), Gastrointestinal (94673, 0.104),
## Gynaecological (2410, 0.003), Hematological (6819, 0.007), Metabolic
## (74865, 0.082), Muscoskeletal/Skin disease (11455, 0.013), Neurological
## (122910, 0.135), Renal/Genitourinary (22125, 0.024), Respiratory (136055,
## 0.149), Sepsis (97598, 0.107), Trauma (40495, 0.044), Undefined (7756,
## 0.008)
## ---------------------------------------------------------------------------
## post.operative
## n missing distinct Info Sum Mean Gmd
## 912509 0 2 0.459 172015 0.1885 0.3059
##
## ---------------------------------------------------------------------------
## code
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 378 0.999 531 482.9 104 106
## .25 .50 .75 .90 .95
## 201 403 703 1212 1413
##
## lowest : 0.01 0.02 0.03 0.04 0.05
## highest: 2201.01 2201.02 2201.03 2201.04 2201.05
## ---------------------------------------------------------------------------
## dx
## n missing distinct
## 912509 0 378
##
## lowest : Abdomen/extremity trauma Abdomen/face trauma Abdomen/multiple trauma Abdomen only trauma Abdomen/pelvis trauma
## highest: Vena cava clipping Vena cava filer insertion Ventriculostomy Weaning from mechanical ventilation (transfer from other unit or hospital only) Whipple surgery for pancreatic cancer
## ---------------------------------------------------------------------------
## number
## n missing distinct Info Mean Gmd
## 912509 0 6 0.165 1.147 0.2811
##
## Value 1 2 3 4 5 6
## Frequency 859197 16144 11817 11814 9081 4456
## Proportion 0.942 0.018 0.013 0.013 0.010 0.005
## ---------------------------------------------------------------------------
## admitdiagnosis
## n missing distinct
## 912509 0 401
##
## lowest : ACIDBASE ACUHEPFAIL ADDISON ADRENNEO AIROBSTRX
## highest: UNSTANGINA VARICBLEED VASCULITIS VIRALMYOSI WEANVENT
## ---------------------------------------------------------------------------
## admitdxpath
## n missing distinct
## 912509 0 401
##
## lowest : admission diagnosis|All Diagnosis|Non-operative|Diagnosis|Cardiovascular|Anaphylaxis admission diagnosis|All Diagnosis|Non-operative|Diagnosis|Cardiovascular|Aneurysm, dissecting aortic admission diagnosis|All Diagnosis|Non-operative|Diagnosis|Cardiovascular|Aneurysm/pseudoaneurysm, other admission diagnosis|All Diagnosis|Non-operative|Diagnosis|Cardiovascular|Angina, stable (asymp or stable pattern of symptoms w/meds)
## highest: admission diagnosis|All Diagnosis|Operative|Diagnosis|Trauma|Extremity/multiple trauma, surgery for admission diagnosis|All Diagnosis|Operative|Diagnosis|Trauma|Extremity only trauma, surgery for admission diagnosis|All Diagnosis|Operative|Diagnosis|Trauma|Face/multiple trauma, surgery for admission diagnosis|All Diagnosis|Operative|Diagnosis|Trauma|Face only trauma, surgery for admission diagnosis|All Diagnosis|Operative|Diagnosis|Trauma|Trauma surgery, other
## ---------------------------------------------------------------------------
## numobs
## n missing distinct Info Mean Gmd .05 .10
## 911985 524 235 1 2610 2596 54 138
## .25 .50 .75 .90 .95
## 548 2110 4389 6262 6790
##
## lowest : 0 1 2 3 4, highest: 5003 5989 6262 6790 8375
## ---------------------------------------------------------------------------
## possible.group
## n missing distinct Info Mean Gmd
## 7454 905055 8 0.868 1030 589.9
##
## Value 312.00 408.02 602.09 802.00 1208.00 1504.00 1701.00 1705.03
## Frequency 2110 678 12 345 348 3551 178 232
## Proportion 0.283 0.091 0.002 0.046 0.047 0.476 0.024 0.031
## ---------------------------------------------------------------------------
## X
## n missing distinct
## 912509 0 13
##
## lowest : ANZICS addition ANZICS Addition. Sub-categories won’t map well, but collapsing to hierarchy (1206) should work ANZICS addition – we have invented this diagnosis code assumes admitted in eICU due to rejection
## highest: Chest pain, unknown origin fuzzy match multiple matches presumably ANZICS only allows the surgical version of this code there are 6 categories for this in eICU
## ---------------------------------------------------------------------------
## c_temp_min
## n missing distinct Info Mean Gmd .05 .10
## 895122 17387 1044 0.996 36.29 0.7768 35.1 35.6
## .25 .50 .75 .90 .95
## 36.1 36.4 36.7 36.9 37.1
##
## lowest : 0.1 0.2 0.5 0.6 0.8, highest: 100.3 100.7 100.8 100.9 101.0
## ---------------------------------------------------------------------------
## c_temp_max
## n missing distinct Info Mean Gmd .05 .10
## 895122 17387 757 0.997 37.32 0.8268 36.40 36.60
## .25 .50 .75 .90 .95
## 36.90 37.17 37.60 38.20 38.70
##
## lowest : 0.10 19.90 21.70 24.40 27.40, highest: 104.50 105.55 105.80 107.20 111.20
## ---------------------------------------------------------------------------
## c_HR_max
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 274 1 102.9 24.95 70 76
## .25 .50 .75 .90 .95
## 87 101 116 132 143
##
## lowest : 5 7 14 15 18, highest: 320 347 360 361 379
## ---------------------------------------------------------------------------
## c_resp_max
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 181 0.998 28.01 9.715 18 19
## .25 .50 .75 .90 .95
## 22 26 31 39 46
##
## lowest : 1 2 3 4 5, highest: 187 194 196 197 199
## ---------------------------------------------------------------------------
## c_sbp_min
## n missing distinct Info Mean Gmd .05 .10
## 912325 184 271 1 92.14 26.45 52 62
## .25 .50 .75 .90 .95
## 78 92 107 121 131
##
## lowest : 1 2 3 4 5, highest: 240 244 246 248 256
## ---------------------------------------------------------------------------
## c_mbp_min
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 282 1 66.76 21.4 41 46
## .25 .50 .75 .90 .95
## 54 64 75 89 104
##
## lowest : 0.13 0.61 0.74 0.87 1.00, highest: 198.00 199.00 200.00 232.00 287.00
## ---------------------------------------------------------------------------
## icu_admit_source2
## n missing distinct
## 912509 0 6
##
## Value Floor OR/Proc Area Direct Admit
## Frequency 154636 176443 98038
## Proportion 0.169 0.193 0.107
##
## Value Emergency Department Other Step-Down Unit
## Frequency 456475 7763 19154
## Proportion 0.500 0.009 0.021
## ---------------------------------------------------------------------------
## icu_type2
## n missing distinct
## 912509 0 8
##
## Trauma ICU (10946, 0.012), Cardiac Care ICU (65472, 0.072),
## Cardiac/Surgical Care ICU (141274, 0.155), Medical/Surgical ICU (468867,
## 0.514), Medical ICU (86772, 0.095), Other ICU (2616, 0.003), Neuro ICU
## (71250, 0.078), Surgical ICU (65312, 0.072)
## ---------------------------------------------------------------------------
## icu_disch_location2
## n missing distinct
## 912509 0 7
##
## Value Floor Death Home SNF/Rehab
## Frequency 665016 61357 88591 14116
## Proportion 0.729 0.067 0.097 0.015
##
## Value Other Other Hospital Step-Down Unit
## Frequency 29315 20636 33478
## Proportion 0.032 0.023 0.037
## ---------------------------------------------------------------------------
## physicianSpeciality2
## n missing distinct
## 912509 0 2
##
## Value Critical Care Speciality-Other
## Frequency 267236 645273
## Proportion 0.293 0.707
## ---------------------------------------------------------------------------
## sofa_respiration_baseline2
## n missing distinct
## 912509 0 2
##
## Value FALSE TRUE
## Frequency 692652 219857
## Proportion 0.759 0.241
## ---------------------------------------------------------------------------
## sofa_renal_baseline2
## n missing distinct
## 912509 0 2
##
## Value FALSE TRUE
## Frequency 881875 30634
## Proportion 0.966 0.034
## ---------------------------------------------------------------------------
## sofa_liver_baseline2
## n missing distinct
## 912509 0 2
##
## Value FALSE TRUE
## Frequency 893444 19065
## Proportion 0.979 0.021
## ---------------------------------------------------------------------------
## SOFA_Change
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 24 0.98 3.519 3.134 0 1
## .25 .50 .75 .90 .95
## 1 3 5 8 9
##
## lowest : 0 1 2 3 4, highest: 19 20 21 22 23
## ---------------------------------------------------------------------------
## SOFA_Positive
## n missing distinct
## 912509 0 2
##
## Value FALSE TRUE
## Frequency 284293 628216
## Proportion 0.312 0.688
## ---------------------------------------------------------------------------
## SOFA_Score
## n missing distinct Info Mean Gmd .05 .10
## 912509 0 24 0.983 3.77 3.341 0 1
## .25 .50 .75 .90 .95
## 1 3 5 8 10
##
## lowest : 0 1 2 3 4, highest: 19 20 21 22 23
## ---------------------------------------------------------------------------
## SOFA_Positive2
## n missing distinct
## 912509 0 2
##
## Value FALSE TRUE
## Frequency 267445 645064
## Proportion 0.293 0.707
## ---------------------------------------------------------------------------
## GCS_qSOFA
## n missing distinct
## 912509 0 2
##
## Value FALSE TRUE
## Frequency 533497 379012
## Proportion 0.585 0.415
## ---------------------------------------------------------------------------
## BP_qSOFA
## n missing distinct
## 912325 184 2
##
## Value FALSE TRUE
## Frequency 314799 597526
## Proportion 0.345 0.655
## ---------------------------------------------------------------------------
## Resp_qSOFA
## n missing distinct
## 912509 0 2
##
## Value FALSE TRUE
## Frequency 208008 704501
## Proportion 0.228 0.772
## ---------------------------------------------------------------------------
## qSOFA_total
## n missing distinct Info Mean Gmd
## 912509 0 4 0.889 1.842 0.9391
##
## Value 0 1 2 3
## Frequency 64765 234728 392737 220279
## Proportion 0.071 0.257 0.430 0.241
## ---------------------------------------------------------------------------
## qSOFA_Positive
## n missing distinct
## 912509 0 2
##
## Value FALSE TRUE
## Frequency 299493 613016
## Proportion 0.328 0.672
## ---------------------------------------------------------------------------
## temp_SIRS
## n missing distinct
## 895122 17387 2
##
## Value FALSE TRUE
## Frequency 618206 276916
## Proportion 0.691 0.309
## ---------------------------------------------------------------------------
## wbc_SIRS
## n missing distinct
## 794753 117756 2
##
## Value FALSE TRUE
## Frequency 424426 370327
## Proportion 0.534 0.466
## ---------------------------------------------------------------------------
## resp_SIRS
## n missing distinct
## 912509 0 2
##
## Value FALSE TRUE
## Frequency 149689 762820
## Proportion 0.164 0.836
## ---------------------------------------------------------------------------
## HR_SIRS
## n missing distinct
## 912509 0 2
##
## Value FALSE TRUE
## Frequency 284634 627875
## Proportion 0.312 0.688
## ---------------------------------------------------------------------------
## SIRS_total
## n missing distinct Info Mean Gmd
## 912509 0 5 0.924 2.233 1.157
##
## Value 0 1 2 3 4
## Frequency 49299 169356 319467 267900 106487
## Proportion 0.054 0.186 0.350 0.294 0.117
## ---------------------------------------------------------------------------
## SIRS_Positive
## n missing distinct
## 912509 0 2
##
## Value FALSE TRUE
## Frequency 218655 693854
## Proportion 0.24 0.76
## ---------------------------------------------------------------------------
## StickyMinutes
## n missing distinct Info Mean Gmd .05 .10
## 540443 372066 301 0.997 252.6 371.6 -60 -60
## .25 .50 .75 .90 .95
## 5 80 400 865 1095
##
## lowest : -60 -55 -50 -45 -40, highest: 1420 1425 1430 1435 1440
## ---------------------------------------------------------------------------
## FuzzyTotal1
## n missing distinct Info Mean Gmd
## 912509 0 3 0.758 1.507 0.6395
##
## Value 0 1 2
## Frequency 78084 293982 540443
## Proportion 0.086 0.322 0.592
## ---------------------------------------------------------------------------
## SimultaneousMinutes
## n missing distinct
## 912509 0 2
##
## Value FALSE TRUE
## Frequency 410001 502508
## Proportion 0.449 0.551
## ---------------------------------------------------------------------------
## SepsisFuzzyLogicPositive
## n missing distinct
## 912509 0 2
##
## Value FALSE TRUE
## Frequency 410001 502508
## Proportion 0.449 0.551
## ---------------------------------------------------------------------------
## SepsisFuzzyLogicPositive2
## n missing distinct
## 912509 0 2
##
## Value FALSE TRUE
## Frequency 410001 502508
## Proportion 0.449 0.551
## ---------------------------------------------------------------------------
## hasDiagnosisCodes
## n missing distinct value
## 912509 0 1 TRUE
##
## Value TRUE
## Frequency 912509
## Proportion 1
## ---------------------------------------------------------------------------
##
## Variables with all observations missing:
##
## [1] hospital_type icu_size17 Seeding/Splitting
Setting the seed and splitting into datasets for training and testing the model
#install.packages("caret")
library(caret); library(Hmisc)##
## Attaching package: 'caret'## The following object is masked from 'package:purrr':
##
## lift## The following object is masked from 'package:survival':
##
## clusterset.seed(999)
ssd_incl <- ssd_incl %>%mutate(SOFA_Change=cut2(SOFA_Change, seq(0,18)))
datasplit <- createDataPartition(ssd_incl$hospital_mortality_ultimate==1,times=1,p=0.7)
ssd_incl_tr <- ssd_incl[datasplit[[1]],]
nrow(ssd_incl_tr)## [1] 638757ssd_incl_tr$hospital_mortality_ultimate<-as.factor (ssd_incl_tr$hospital_mortality_ultimate)
ssd_incl_tr$sepsis_outcome<-as.factor (ssd_incl_tr$sepsis_outcome)18 Baseline Mortality
GLM and Train on training set and predictions/performance (ROC, SENS, SPEC, PPV, NPV, accuracy) on test set
library(sjPlot); library(ROCR); library(Hmisc); library(pROC); library(randomForest)## Loading required package: gplots##
## Attaching package: 'gplots'## The following object is masked from 'package:stats':
##
## lowess## Type 'citation("pROC")' for a citation.##
## Attaching package: 'pROC'## The following objects are masked from 'package:stats':
##
## cov, smooth, var## randomForest 4.6-12## Type rfNews() to see new features/changes/bug fixes.##
## Attaching package: 'randomForest'## The following object is masked from 'package:ggplot2':
##
## margin## The following object is masked from 'package:dplyr':
##
## combineBaseline_Hosp_Mort_tr<-glm(hospital_mortality_ultimate ~ age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status + hospital_size + physicianSpeciality2 + hospitaldischargeyear + dialysis + aids + hepaticfailure + diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer + thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline, data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(Baseline_Hosp_Mort_tr)
#sjt.glm(Baseline_Hosp_Mort_tr)
#drop1(Baseline_Hosp_Mort_tr,test="Chisq")
summary(Baseline_Hosp_Mort_tr)##
## Call:
## glm(formula = hospital_mortality_ultimate ~ age_Ranges + gender2 +
## ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status +
## hospital_size + physicianSpeciality2 + hospitaldischargeyear +
## dialysis + aids + hepaticfailure + diabetes + immunosuppression +
## leukemia + lymphoma + metastaticcancer + thrombolytics +
## sofa_respiration_baseline2 + cardiovascular_baseline, family = "binomial",
## data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.6276 -0.4936 -0.3733 -0.2677 3.1470
##
## Coefficients:
## Estimate Std. Error z value
## (Intercept) -2.250932 0.050527 -44.549
## age_Ranges(25,35] 0.229442 0.049062 4.677
## age_Ranges(35,45] 0.418396 0.045277 9.241
## age_Ranges(45,55] 0.757457 0.041906 18.075
## age_Ranges(55,65] 1.026053 0.041085 24.974
## age_Ranges(65,75] 1.282694 0.040902 31.360
## age_Ranges(75,85] 1.578865 0.040839 38.661
## age_Ranges(85,100] 1.824671 0.041638 43.822
## gender2Female -0.067416 0.008936 -7.544
## gender2Other/Unknown 1.840225 0.177099 10.391
## ethnicity2African American -0.006201 0.014720 -0.421
## ethnicity2Hispanic 0.075543 0.021220 3.560
## ethnicity2Asian 0.140192 0.037547 3.734
## ethnicity2Native American 0.413400 0.048960 8.444
## ethnicity2Other/Unknown 0.196662 0.018991 10.355
## BMI_Ranges(18.5,25] -0.328096 0.018575 -17.663
## BMI_Ranges(25,35] -0.504116 0.018321 -27.516
## BMI_Ranges(35,200] -0.375889 0.020472 -18.361
## BMI_RangesOther/Unknown -0.051990 0.026790 -1.941
## icu_admit_source2OR/Proc Area -1.475248 0.017523 -84.191
## icu_admit_source2Direct Admit -0.393215 0.015587 -25.227
## icu_admit_source2Emergency Department -0.489498 0.010756 -45.509
## icu_admit_source2Other -0.093568 0.040517 -2.309
## icu_admit_source2Step-Down Unit 0.167136 0.024843 6.728
## hospital_teaching_statusf -0.053537 0.032153 -1.665
## hospital_teaching_statust -0.144347 0.032493 -4.442
## hospital_size<100 -0.560120 0.036404 -15.386
## hospital_size100-249 -0.057453 0.025300 -2.271
## hospital_size250-500 0.085279 0.025555 3.337
## hospital_size>500 0.229786 0.023791 9.659
## physicianSpeciality2Speciality-Other -0.431226 0.009850 -43.778
## hospitaldischargeyear2011 -0.024672 0.016825 -1.466
## hospitaldischargeyear2012 -0.070520 0.016231 -4.345
## hospitaldischargeyear2013 -0.121428 0.015964 -7.607
## hospitaldischargeyear2014 -0.172203 0.015908 -10.825
## hospitaldischargeyear2015-16 -0.139292 0.015732 -8.854
## dialysis1 0.330458 0.022266 14.841
## aids1 0.556828 0.117003 4.759
## hepaticfailureTRUE 0.760290 0.024386 31.178
## diabetes1 -0.279194 0.011551 -24.170
## immunosuppression1 0.379349 0.025108 15.108
## leukemia1 0.511737 0.039519 12.949
## lymphoma1 0.287931 0.056424 5.103
## metastaticcancer1 0.681493 0.026194 26.017
## thrombolytics1 -0.034820 0.034356 -1.014
## sofa_respiration_baseline2TRUE 0.086748 0.010077 8.608
## cardiovascular_baseline1 0.110204 0.010275 10.726
## Pr(>|z|)
## (Intercept) < 2e-16 ***
## age_Ranges(25,35] 2.92e-06 ***
## age_Ranges(35,45] < 2e-16 ***
## age_Ranges(45,55] < 2e-16 ***
## age_Ranges(55,65] < 2e-16 ***
## age_Ranges(65,75] < 2e-16 ***
## age_Ranges(75,85] < 2e-16 ***
## age_Ranges(85,100] < 2e-16 ***
## gender2Female 4.55e-14 ***
## gender2Other/Unknown < 2e-16 ***
## ethnicity2African American 0.673568
## ethnicity2Hispanic 0.000371 ***
## ethnicity2Asian 0.000189 ***
## ethnicity2Native American < 2e-16 ***
## ethnicity2Other/Unknown < 2e-16 ***
## BMI_Ranges(18.5,25] < 2e-16 ***
## BMI_Ranges(25,35] < 2e-16 ***
## BMI_Ranges(35,200] < 2e-16 ***
## BMI_RangesOther/Unknown 0.052304 .
## icu_admit_source2OR/Proc Area < 2e-16 ***
## icu_admit_source2Direct Admit < 2e-16 ***
## icu_admit_source2Emergency Department < 2e-16 ***
## icu_admit_source2Other 0.020926 *
## icu_admit_source2Step-Down Unit 1.72e-11 ***
## hospital_teaching_statusf 0.095900 .
## hospital_teaching_statust 8.90e-06 ***
## hospital_size<100 < 2e-16 ***
## hospital_size100-249 0.023158 *
## hospital_size250-500 0.000847 ***
## hospital_size>500 < 2e-16 ***
## physicianSpeciality2Speciality-Other < 2e-16 ***
## hospitaldischargeyear2011 0.142539
## hospitaldischargeyear2012 1.40e-05 ***
## hospitaldischargeyear2013 2.81e-14 ***
## hospitaldischargeyear2014 < 2e-16 ***
## hospitaldischargeyear2015-16 < 2e-16 ***
## dialysis1 < 2e-16 ***
## aids1 1.94e-06 ***
## hepaticfailureTRUE < 2e-16 ***
## diabetes1 < 2e-16 ***
## immunosuppression1 < 2e-16 ***
## leukemia1 < 2e-16 ***
## lymphoma1 3.34e-07 ***
## metastaticcancer1 < 2e-16 ***
## thrombolytics1 0.310814
## sofa_respiration_baseline2TRUE < 2e-16 ***
## cardiovascular_baseline1 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 399603 on 638756 degrees of freedom
## Residual deviance: 370829 on 638710 degrees of freedom
## AIC: 370923
##
## Number of Fisher Scoring iterations: 6ssd_incl_te <- ssd_incl[-datasplit[[1]],]
nrow(ssd_incl_te)## [1] 273752ssd_incl_te$BaselineHospMortPred <- predict(Baseline_Hosp_Mort_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
ssd_incl_te$BaselineDec <-cut2(ssd_incl_te$BaselineHospMortPred, g=10)
BaselineMort.Pred <- prediction(ssd_incl_te$BaselineHospMortPred, ssd_incl_te$hospital_mortality_ultimate)
BaselineMort.Perf <- performance(BaselineMort.Pred, "tpr", "fpr")
plot(BaselineMort.Perf, main = "Baseline Mortality
Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(BaselineMort.Pred,"auc")@y.values[[1]],3))) 
performance(BaselineMort.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.7063341
##
##
## Slot "alpha.values":
## list()BaselineMort.Pred.roc <- roc(hospital_mortality_ultimate~BaselineHospMortPred,data=ssd_incl_te,algorithm=3,ci=TRUE)
try(ci(BaselineMort.Pred.roc, conf.level=0.99))## 99% CI: 0.7021-0.7105 (DeLong)ggplot(calibration(as.factor(hospital_mortality_ultimate==0)~BaselineHospMortPred, data = ssd_incl_te))+ggtitle("Calibration of Baseline Mortality Prediction")## Warning: Removed 2 rows containing missing values (geom_errorbar).
qplot(BaselineHospMortPred, data = ssd_incl_te)+ggtitle("Histogram of Baseline Mortality Predictions") ## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
19 Cross validation
partitions the data into 5 groups and then uses the 4 groups to predict the 5th group. It does this 5 times and then takes the average, ROC curves,
Train/glm completed on the train dataset; prediction and performance completed on the test dataset.
SIRS1_ADJ_Hosp_Mort_tr<-glm(hospital_mortality_ultimate ~ as.factor(SIRS_total) + age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status + hospital_size + physicianSpeciality2 + hospitaldischargeyear + dialysis + aids + hepaticfailure + diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer + thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline, data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SIRS1_ADJ_Hosp_Mort_tr)
#sjt.glm(SIRS1_ADJ_Hosp_Mort_tr)
#drop1(SIRS1_ADJ_Hosp_Mort_tr,test="Chisq")
summary(SIRS1_ADJ_Hosp_Mort_tr)##
## Call:
## glm(formula = hospital_mortality_ultimate ~ as.factor(SIRS_total) +
## age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 +
## hospital_teaching_status + hospital_size + physicianSpeciality2 +
## hospitaldischargeyear + dialysis + aids + hepaticfailure +
## diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer +
## thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline,
## family = "binomial", data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.9172 -0.4682 -0.3119 -0.1981 3.5016
##
## Coefficients:
## Estimate Std. Error z value
## (Intercept) -4.4033273 0.0669083 -65.811
## as.factor(SIRS_total)1 0.5500217 0.0456838 12.040
## as.factor(SIRS_total)2 1.3688529 0.0433032 31.611
## as.factor(SIRS_total)3 2.1573331 0.0430423 50.121
## as.factor(SIRS_total)4 2.9515996 0.0434567 67.920
## age_Ranges(25,35] 0.2570893 0.0496437 5.179
## age_Ranges(35,45] 0.4780080 0.0458350 10.429
## age_Ranges(45,55] 0.8663145 0.0424222 20.421
## age_Ranges(55,65] 1.1531623 0.0415890 27.728
## age_Ranges(65,75] 1.4393826 0.0414225 34.749
## age_Ranges(75,85] 1.7665530 0.0413879 42.683
## age_Ranges(85,100] 2.0380748 0.0422738 48.211
## gender2Female -0.0819955 0.0092092 -8.904
## gender2Other/Unknown 1.6827393 0.1915034 8.787
## ethnicity2African American 0.0242863 0.0151634 1.602
## ethnicity2Hispanic 0.0695744 0.0219392 3.171
## ethnicity2Asian 0.1390930 0.0388335 3.582
## ethnicity2Native American 0.3755676 0.0506218 7.419
## ethnicity2Other/Unknown 0.2039346 0.0196154 10.397
## BMI_Ranges(18.5,25] -0.2889067 0.0192326 -15.022
## BMI_Ranges(25,35] -0.4412794 0.0189637 -23.270
## BMI_Ranges(35,200] -0.3240074 0.0211512 -15.319
## BMI_RangesOther/Unknown 0.1534701 0.0278737 5.506
## icu_admit_source2OR/Proc Area -1.5161274 0.0178884 -84.755
## icu_admit_source2Direct Admit -0.2696384 0.0161692 -16.676
## icu_admit_source2Emergency Department -0.3857470 0.0111422 -34.620
## icu_admit_source2Other -0.1105148 0.0419398 -2.635
## icu_admit_source2Step-Down Unit 0.1265906 0.0257888 4.909
## hospital_teaching_statusf -0.0858692 0.0331260 -2.592
## hospital_teaching_statust -0.2064886 0.0336210 -6.142
## hospital_size<100 -0.4533840 0.0372893 -12.159
## hospital_size100-249 0.0006072 0.0260174 0.023
## hospital_size250-500 0.0593403 0.0262684 2.259
## hospital_size>500 0.2299083 0.0245490 9.365
## physicianSpeciality2Speciality-Other -0.2499178 0.0101859 -24.536
## hospitaldischargeyear2011 -0.0510514 0.0174171 -2.931
## hospitaldischargeyear2012 -0.0858751 0.0167892 -5.115
## hospitaldischargeyear2013 -0.1243127 0.0165072 -7.531
## hospitaldischargeyear2014 -0.1521628 0.0164394 -9.256
## hospitaldischargeyear2015-16 -0.1431594 0.0162584 -8.805
## dialysis1 0.3714920 0.0230898 16.089
## aids1 0.4083058 0.1206597 3.384
## hepaticfailureTRUE 0.7758289 0.0253976 30.547
## diabetes1 -0.2798912 0.0118792 -23.561
## immunosuppression1 0.2714149 0.0259178 10.472
## leukemia1 0.2929703 0.0409368 7.157
## lymphoma1 0.1928275 0.0583328 3.306
## metastaticcancer1 0.6544569 0.0271533 24.102
## thrombolytics1 0.1077904 0.0355692 3.030
## sofa_respiration_baseline2TRUE 0.0299530 0.0103894 2.883
## cardiovascular_baseline1 0.1949686 0.0106352 18.332
## Pr(>|z|)
## (Intercept) < 2e-16 ***
## as.factor(SIRS_total)1 < 2e-16 ***
## as.factor(SIRS_total)2 < 2e-16 ***
## as.factor(SIRS_total)3 < 2e-16 ***
## as.factor(SIRS_total)4 < 2e-16 ***
## age_Ranges(25,35] 2.23e-07 ***
## age_Ranges(35,45] < 2e-16 ***
## age_Ranges(45,55] < 2e-16 ***
## age_Ranges(55,65] < 2e-16 ***
## age_Ranges(65,75] < 2e-16 ***
## age_Ranges(75,85] < 2e-16 ***
## age_Ranges(85,100] < 2e-16 ***
## gender2Female < 2e-16 ***
## gender2Other/Unknown < 2e-16 ***
## ethnicity2African American 0.109234
## ethnicity2Hispanic 0.001518 **
## ethnicity2Asian 0.000341 ***
## ethnicity2Native American 1.18e-13 ***
## ethnicity2Other/Unknown < 2e-16 ***
## BMI_Ranges(18.5,25] < 2e-16 ***
## BMI_Ranges(25,35] < 2e-16 ***
## BMI_Ranges(35,200] < 2e-16 ***
## BMI_RangesOther/Unknown 3.67e-08 ***
## icu_admit_source2OR/Proc Area < 2e-16 ***
## icu_admit_source2Direct Admit < 2e-16 ***
## icu_admit_source2Emergency Department < 2e-16 ***
## icu_admit_source2Other 0.008412 **
## icu_admit_source2Step-Down Unit 9.17e-07 ***
## hospital_teaching_statusf 0.009536 **
## hospital_teaching_statust 8.17e-10 ***
## hospital_size<100 < 2e-16 ***
## hospital_size100-249 0.981380
## hospital_size250-500 0.023883 *
## hospital_size>500 < 2e-16 ***
## physicianSpeciality2Speciality-Other < 2e-16 ***
## hospitaldischargeyear2011 0.003378 **
## hospitaldischargeyear2012 3.14e-07 ***
## hospitaldischargeyear2013 5.04e-14 ***
## hospitaldischargeyear2014 < 2e-16 ***
## hospitaldischargeyear2015-16 < 2e-16 ***
## dialysis1 < 2e-16 ***
## aids1 0.000715 ***
## hepaticfailureTRUE < 2e-16 ***
## diabetes1 < 2e-16 ***
## immunosuppression1 < 2e-16 ***
## leukemia1 8.27e-13 ***
## lymphoma1 0.000948 ***
## metastaticcancer1 < 2e-16 ***
## thrombolytics1 0.002442 **
## sofa_respiration_baseline2TRUE 0.003939 **
## cardiovascular_baseline1 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 399603 on 638756 degrees of freedom
## Residual deviance: 342338 on 638706 degrees of freedom
## AIC: 342440
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$SIRS1ADJHospMortPred <- predict(SIRS1_ADJ_Hosp_Mort_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
SIRS1ADJMort.Pred <- prediction(ssd_incl_te$SIRS1ADJHospMortPred, ssd_incl_te$hospital_mortality_ultimate)
SIRS1ADJMort.Perf <- performance(SIRS1ADJMort.Pred, "tpr", "fpr")
plot(SIRS1ADJMort.Perf, main = "SIRS Continuous Adjusted
Mortality Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SIRS1ADJMort.Pred,"auc")@y.values[[1]],3))) 
performance(SIRS1ADJMort.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.781489
##
##
## Slot "alpha.values":
## list()SIRS1ADJMort.Pred.roc <- roc(hospital_mortality_ultimate~ SIRS1ADJHospMortPred,data=ssd_incl_te)
ci(SIRS1ADJMort.Pred.roc, conf.level=0.99)## 99% CI: 0.7779-0.7851 (DeLong)ggplot(calibration(as.factor(hospital_mortality_ultimate==0)~SIRS1ADJHospMortPred, data = ssd_incl_te))+ggtitle("Calibration of ADJ Mortality SIRS Total Prediction")## Warning: Removed 1 rows containing missing values (geom_errorbar).
qplot(SIRS1ADJHospMortPred, data = ssd_incl_te)+ggtitle("Histogram of ADJ Mortality SIRS Total Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
SIRS2_ADJ_Hosp_Mort_tr<-glm(hospital_mortality_ultimate ~ as.factor(SIRS_Positive) + age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status + hospital_size + physicianSpeciality2 + hospitaldischargeyear + dialysis + aids + hepaticfailure + diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer + thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline, data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SIRS2_ADJ_Hosp_Mort_tr)
#sjt.glm(SIRS2_ADJ_Hosp_Mort_tr)
#drop1(SIRS2_ADJ_Hosp_Mort_tr,test="Chisq")
summary(SIRS2_ADJ_Hosp_Mort_tr)##
## Call:
## glm(formula = hospital_mortality_ultimate ~ as.factor(SIRS_Positive) +
## age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 +
## hospital_teaching_status + hospital_size + physicianSpeciality2 +
## hospitaldischargeyear + dialysis + aids + hepaticfailure +
## diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer +
## thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline,
## family = "binomial", data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.7460 -0.5041 -0.3420 -0.2201 3.5149
##
## Coefficients:
## Estimate Std. Error z value
## (Intercept) -3.7353712 0.0533820 -69.974
## as.factor(SIRS_Positive)TRUE 1.5501007 0.0166049 93.352
## age_Ranges(25,35] 0.2341878 0.0491700 4.763
## age_Ranges(35,45] 0.4422036 0.0453825 9.744
## age_Ranges(45,55] 0.8133442 0.0420051 19.363
## age_Ranges(55,65] 1.1012734 0.0411813 26.742
## age_Ranges(65,75] 1.3673261 0.0410022 33.348
## age_Ranges(75,85] 1.6711568 0.0409490 40.811
## age_Ranges(85,100] 1.9118926 0.0417794 45.762
## gender2Female -0.0827101 0.0090284 -9.161
## gender2Other/Unknown 1.8353850 0.1840623 9.972
## ethnicity2African American -0.0001864 0.0148589 -0.013
## ethnicity2Hispanic 0.0817242 0.0214713 3.806
## ethnicity2Asian 0.1443329 0.0380038 3.798
## ethnicity2Native American 0.4002222 0.0495443 8.078
## ethnicity2Other/Unknown 0.2080260 0.0192215 10.823
## BMI_Ranges(18.5,25] -0.2970890 0.0187827 -15.817
## BMI_Ranges(25,35] -0.4496792 0.0185246 -24.275
## BMI_Ranges(35,200] -0.3290523 0.0206832 -15.909
## BMI_RangesOther/Unknown 0.0630207 0.0272240 2.315
## icu_admit_source2OR/Proc Area -1.4644246 0.0176261 -83.083
## icu_admit_source2Direct Admit -0.3052330 0.0158092 -19.307
## icu_admit_source2Emergency Department -0.4319494 0.0108865 -39.677
## icu_admit_source2Other -0.0931470 0.0409624 -2.274
## icu_admit_source2Step-Down Unit 0.1531999 0.0251306 6.096
## hospital_teaching_statusf -0.1022073 0.0324836 -3.146
## hospital_teaching_statust -0.2091128 0.0328309 -6.369
## hospital_size<100 -0.4951941 0.0367083 -13.490
## hospital_size100-249 -0.0014247 0.0255296 -0.056
## hospital_size250-500 0.1068927 0.0257786 4.147
## hospital_size>500 0.2642215 0.0240025 11.008
## physicianSpeciality2Speciality-Other -0.3415485 0.0099516 -34.321
## hospitaldischargeyear2011 -0.0458901 0.0170360 -2.694
## hospitaldischargeyear2012 -0.0964850 0.0164294 -5.873
## hospitaldischargeyear2013 -0.1540092 0.0161579 -9.531
## hospitaldischargeyear2014 -0.1953215 0.0160985 -12.133
## hospitaldischargeyear2015-16 -0.1779590 0.0159188 -11.179
## dialysis1 0.3472659 0.0225635 15.391
## aids1 0.5049126 0.1177279 4.289
## hepaticfailureTRUE 0.7541447 0.0247125 30.517
## diabetes1 -0.2783472 0.0116522 -23.888
## immunosuppression1 0.3302446 0.0252849 13.061
## leukemia1 0.4274687 0.0398403 10.730
## lymphoma1 0.2517849 0.0569702 4.420
## metastaticcancer1 0.6437225 0.0264597 24.328
## thrombolytics1 0.0868257 0.0348889 2.489
## sofa_respiration_baseline2TRUE 0.0241130 0.0101831 2.368
## cardiovascular_baseline1 0.1469103 0.0104055 14.119
## Pr(>|z|)
## (Intercept) < 2e-16 ***
## as.factor(SIRS_Positive)TRUE < 2e-16 ***
## age_Ranges(25,35] 1.91e-06 ***
## age_Ranges(35,45] < 2e-16 ***
## age_Ranges(45,55] < 2e-16 ***
## age_Ranges(55,65] < 2e-16 ***
## age_Ranges(65,75] < 2e-16 ***
## age_Ranges(75,85] < 2e-16 ***
## age_Ranges(85,100] < 2e-16 ***
## gender2Female < 2e-16 ***
## gender2Other/Unknown < 2e-16 ***
## ethnicity2African American 0.989992
## ethnicity2Hispanic 0.000141 ***
## ethnicity2Asian 0.000146 ***
## ethnicity2Native American 6.58e-16 ***
## ethnicity2Other/Unknown < 2e-16 ***
## BMI_Ranges(18.5,25] < 2e-16 ***
## BMI_Ranges(25,35] < 2e-16 ***
## BMI_Ranges(35,200] < 2e-16 ***
## BMI_RangesOther/Unknown 0.020619 *
## icu_admit_source2OR/Proc Area < 2e-16 ***
## icu_admit_source2Direct Admit < 2e-16 ***
## icu_admit_source2Emergency Department < 2e-16 ***
## icu_admit_source2Other 0.022968 *
## icu_admit_source2Step-Down Unit 1.09e-09 ***
## hospital_teaching_statusf 0.001653 **
## hospital_teaching_statust 1.90e-10 ***
## hospital_size<100 < 2e-16 ***
## hospital_size100-249 0.955496
## hospital_size250-500 3.37e-05 ***
## hospital_size>500 < 2e-16 ***
## physicianSpeciality2Speciality-Other < 2e-16 ***
## hospitaldischargeyear2011 0.007066 **
## hospitaldischargeyear2012 4.29e-09 ***
## hospitaldischargeyear2013 < 2e-16 ***
## hospitaldischargeyear2014 < 2e-16 ***
## hospitaldischargeyear2015-16 < 2e-16 ***
## dialysis1 < 2e-16 ***
## aids1 1.80e-05 ***
## hepaticfailureTRUE < 2e-16 ***
## diabetes1 < 2e-16 ***
## immunosuppression1 < 2e-16 ***
## leukemia1 < 2e-16 ***
## lymphoma1 9.89e-06 ***
## metastaticcancer1 < 2e-16 ***
## thrombolytics1 0.012824 *
## sofa_respiration_baseline2TRUE 0.017888 *
## cardiovascular_baseline1 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 399603 on 638756 degrees of freedom
## Residual deviance: 358142 on 638709 degrees of freedom
## AIC: 358238
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$SIRS2ADJHospMortPred <- predict (SIRS2_ADJ_Hosp_Mort_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
SIRS2ADJMort.Pred <- prediction(ssd_incl_te$SIRS2ADJHospMortPred, ssd_incl_te$hospital_mortality_ultimate)
SIRS2ADJMort.Perf <- performance(SIRS2ADJMort.Pred, "tpr", "fpr")
plot(SIRS2ADJMort.Perf, main = "SIRS Positive Adjusted
Mortality Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SIRS2ADJMort.Pred,"auc")@y.values[[1]],3))) 
performance(SIRS2ADJMort.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.7423965
##
##
## Slot "alpha.values":
## list()SIRS2ADJMort.Pred.roc <- roc(hospital_mortality_ultimate~ SIRS2ADJHospMortPred,data=ssd_incl_te)
ci(SIRS2ADJMort.Pred.roc, conf.level=0.99)## 99% CI: 0.7386-0.7462 (DeLong)ggplot(calibration(as.factor(hospital_mortality_ultimate==0)~SIRS2ADJHospMortPred, data = ssd_incl_te))+ggtitle("Calibration of ADJ Mortality SIRS Positive Prediction")## Warning: Removed 2 rows containing missing values (geom_errorbar).
qplot(SIRS2ADJHospMortPred, data = ssd_incl_te)+ggtitle("Histogram of ADJ Mortality SIRS Positive Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
SOFA1_ADJ_Hosp_Mort_tr<-glm(hospital_mortality_ultimate ~ as.factor(SOFA_Change) + age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status + hospital_size + physicianSpeciality2 + hospitaldischargeyear + dialysis + aids + hepaticfailure + diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer + thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline, data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SOFA1_ADJ_Hosp_Mort_tr)
#sjt.glm(SOFA1_ADJ_Hosp_Mort_tr)
#drop1(SOFA1_ADJ_Hosp_Mort_tr,test="Chisq")
summary(SOFA1_ADJ_Hosp_Mort_tr)##
## Call:
## glm(formula = hospital_mortality_ultimate ~ as.factor(SOFA_Change) +
## age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 +
## hospital_teaching_status + hospital_size + physicianSpeciality2 +
## hospitaldischargeyear + dialysis + aids + hepaticfailure +
## diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer +
## thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline,
## family = "binomial", data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.4428 -0.4058 -0.2414 -0.1429 3.5627
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.77549 0.07031 -67.926 < 2e-16
## as.factor(SOFA_Change) 1 0.51755 0.04790 10.806 < 2e-16
## as.factor(SOFA_Change) 2 0.94833 0.04766 19.897 < 2e-16
## as.factor(SOFA_Change) 3 1.50675 0.04653 32.381 < 2e-16
## as.factor(SOFA_Change) 4 1.93885 0.04604 42.111 < 2e-16
## as.factor(SOFA_Change) 5 2.36041 0.04592 51.399 < 2e-16
## as.factor(SOFA_Change) 6 2.59633 0.04636 56.005 < 2e-16
## as.factor(SOFA_Change) 7 3.12266 0.04626 67.496 < 2e-16
## as.factor(SOFA_Change) 8 3.39608 0.04699 72.268 < 2e-16
## as.factor(SOFA_Change) 9 3.72733 0.04787 77.864 < 2e-16
## as.factor(SOFA_Change)10 4.02493 0.04912 81.938 < 2e-16
## as.factor(SOFA_Change)11 4.45056 0.05076 87.686 < 2e-16
## as.factor(SOFA_Change)12 4.70142 0.05401 87.053 < 2e-16
## as.factor(SOFA_Change)13 5.02838 0.05860 85.804 < 2e-16
## as.factor(SOFA_Change)14 5.30110 0.06647 79.756 < 2e-16
## as.factor(SOFA_Change)15 5.59238 0.07855 71.199 < 2e-16
## as.factor(SOFA_Change)16 6.00864 0.09983 60.186 < 2e-16
## as.factor(SOFA_Change)17 6.35174 0.14533 43.706 < 2e-16
## as.factor(SOFA_Change)[18,23] 6.72698 0.15509 43.375 < 2e-16
## age_Ranges(25,35] 0.15128 0.05287 2.861 0.004220
## age_Ranges(35,45] 0.25870 0.04883 5.298 1.17e-07
## age_Ranges(45,55] 0.52916 0.04508 11.738 < 2e-16
## age_Ranges(55,65] 0.75028 0.04416 16.991 < 2e-16
## age_Ranges(65,75] 1.02159 0.04396 23.241 < 2e-16
## age_Ranges(75,85] 1.32943 0.04389 30.289 < 2e-16
## age_Ranges(85,100] 1.60371 0.04479 35.805 < 2e-16
## gender2Female 0.07669 0.00984 7.794 6.49e-15
## gender2Other/Unknown 2.04771 0.20408 10.034 < 2e-16
## ethnicity2African American -0.16619 0.01631 -10.191 < 2e-16
## ethnicity2Hispanic -0.08934 0.02351 -3.800 0.000145
## ethnicity2Asian -0.03644 0.04193 -0.869 0.384822
## ethnicity2Native American -0.06771 0.05532 -1.224 0.220960
## ethnicity2Other/Unknown 0.05483 0.02113 2.595 0.009461
## BMI_Ranges(18.5,25] -0.30707 0.02044 -15.020 < 2e-16
## BMI_Ranges(25,35] -0.54280 0.02019 -26.879 < 2e-16
## BMI_Ranges(35,200] -0.55380 0.02260 -24.501 < 2e-16
## BMI_RangesOther/Unknown 0.08910 0.02987 2.983 0.002858
## icu_admit_source2OR/Proc Area -1.48921 0.01886 -78.945 < 2e-16
## icu_admit_source2Direct Admit -0.31881 0.01750 -18.221 < 2e-16
## icu_admit_source2Emergency Department -0.32144 0.01195 -26.897 < 2e-16
## icu_admit_source2Other -0.10907 0.04515 -2.416 0.015704
## icu_admit_source2Step-Down Unit 0.18099 0.02766 6.544 5.98e-11
## hospital_teaching_statusf 0.17821 0.03549 5.021 5.14e-07
## hospital_teaching_statust 0.05926 0.03605 1.644 0.100152
## hospital_size<100 -0.34572 0.03910 -8.842 < 2e-16
## hospital_size100-249 -0.04716 0.02768 -1.704 0.088453
## hospital_size250-500 -0.04072 0.02799 -1.455 0.145687
## hospital_size>500 0.13895 0.02617 5.310 1.10e-07
## physicianSpeciality2Speciality-Other -0.06818 0.01100 -6.198 5.73e-10
## hospitaldischargeyear2011 -0.04850 0.01857 -2.611 0.009015
## hospitaldischargeyear2012 -0.05542 0.01792 -3.093 0.001982
## hospitaldischargeyear2013 -0.05490 0.01758 -3.123 0.001791
## hospitaldischargeyear2014 -0.11714 0.01753 -6.684 2.33e-11
## hospitaldischargeyear2015-16 -0.16845 0.01737 -9.700 < 2e-16
## dialysis1 0.72138 0.02434 29.635 < 2e-16
## aids1 0.39881 0.13002 3.067 0.002160
## hepaticfailureTRUE 0.38666 0.02700 14.322 < 2e-16
## diabetes1 -0.25365 0.01263 -20.077 < 2e-16
## immunosuppression1 0.32414 0.02816 11.509 < 2e-16
## leukemia1 0.13061 0.04464 2.926 0.003435
## lymphoma1 0.12959 0.06356 2.039 0.041448
## metastaticcancer1 0.79487 0.02945 26.992 < 2e-16
## thrombolytics1 0.23682 0.03927 6.030 1.64e-09
## sofa_respiration_baseline2TRUE 0.41765 0.01111 37.599 < 2e-16
## cardiovascular_baseline1 0.02912 0.01128 2.582 0.009813
##
## (Intercept) ***
## as.factor(SOFA_Change) 1 ***
## as.factor(SOFA_Change) 2 ***
## as.factor(SOFA_Change) 3 ***
## as.factor(SOFA_Change) 4 ***
## as.factor(SOFA_Change) 5 ***
## as.factor(SOFA_Change) 6 ***
## as.factor(SOFA_Change) 7 ***
## as.factor(SOFA_Change) 8 ***
## as.factor(SOFA_Change) 9 ***
## as.factor(SOFA_Change)10 ***
## as.factor(SOFA_Change)11 ***
## as.factor(SOFA_Change)12 ***
## as.factor(SOFA_Change)13 ***
## as.factor(SOFA_Change)14 ***
## as.factor(SOFA_Change)15 ***
## as.factor(SOFA_Change)16 ***
## as.factor(SOFA_Change)17 ***
## as.factor(SOFA_Change)[18,23] ***
## age_Ranges(25,35] **
## age_Ranges(35,45] ***
## age_Ranges(45,55] ***
## age_Ranges(55,65] ***
## age_Ranges(65,75] ***
## age_Ranges(75,85] ***
## age_Ranges(85,100] ***
## gender2Female ***
## gender2Other/Unknown ***
## ethnicity2African American ***
## ethnicity2Hispanic ***
## ethnicity2Asian
## ethnicity2Native American
## ethnicity2Other/Unknown **
## BMI_Ranges(18.5,25] ***
## BMI_Ranges(25,35] ***
## BMI_Ranges(35,200] ***
## BMI_RangesOther/Unknown **
## icu_admit_source2OR/Proc Area ***
## icu_admit_source2Direct Admit ***
## icu_admit_source2Emergency Department ***
## icu_admit_source2Other *
## icu_admit_source2Step-Down Unit ***
## hospital_teaching_statusf ***
## hospital_teaching_statust
## hospital_size<100 ***
## hospital_size100-249 .
## hospital_size250-500
## hospital_size>500 ***
## physicianSpeciality2Speciality-Other ***
## hospitaldischargeyear2011 **
## hospitaldischargeyear2012 **
## hospitaldischargeyear2013 **
## hospitaldischargeyear2014 ***
## hospitaldischargeyear2015-16 ***
## dialysis1 ***
## aids1 **
## hepaticfailureTRUE ***
## diabetes1 ***
## immunosuppression1 ***
## leukemia1 **
## lymphoma1 *
## metastaticcancer1 ***
## thrombolytics1 ***
## sofa_respiration_baseline2TRUE ***
## cardiovascular_baseline1 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 399603 on 638756 degrees of freedom
## Residual deviance: 298942 on 638692 degrees of freedom
## AIC: 299072
##
## Number of Fisher Scoring iterations: 7ssd_incl_te$SOFA1ADJHospMortPred <- predict (SOFA1_ADJ_Hosp_Mort_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
SOFA1ADJMort.Pred <- prediction(ssd_incl_te$SOFA1ADJHospMortPred, ssd_incl_te$hospital_mortality_ultimate)
SOFA1ADJMort.Perf <- performance(SOFA1ADJMort.Pred, "tpr", "fpr")
plot(SOFA1ADJMort.Perf, main = "SOFA Continuous Adjusted
Mortality Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SOFA1ADJMort.Pred,"auc")@y.values[[1]],3))) 
performance(SOFA1ADJMort.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.8472926
##
##
## Slot "alpha.values":
## list()SOFA1ADJMort.Pred.roc <- roc(hospital_mortality_ultimate~ SOFA1ADJHospMortPred,data=ssd_incl_te)
ci(SOFA1ADJMort.Pred.roc, conf.level=0.99)## 99% CI: 0.8442-0.8504 (DeLong)ggplot(calibration(as.factor(hospital_mortality_ultimate==0)~SOFA1ADJHospMortPred, data = ssd_incl_te))+ggtitle("Calibration of ADJ Mortality SOFA Total Prediction")
qplot(SOFA1ADJHospMortPred, data = ssd_incl_te)+ggtitle("Histogram of ADJ Mortality SOFA Total Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
SOFA2_ADJ_Hosp_Mort_tr<-glm(hospital_mortality_ultimate ~ as.factor(SOFA_Positive) + age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status + hospital_size + physicianSpeciality2 + hospitaldischargeyear + dialysis + aids + hepaticfailure + diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer + thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline, data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SOFA2_ADJ_Hosp_Mort_tr)
#sjt.glm(SOFA2_ADJ_Hosp_Mort_tr)
#drop1(SOFA2_ADJ_Hosp_Mort_tr,test="Chisq")
summary(SOFA2_ADJ_Hosp_Mort_tr)##
## Call:
## glm(formula = hospital_mortality_ultimate ~ as.factor(SOFA_Positive) +
## age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 +
## hospital_teaching_status + hospital_size + physicianSpeciality2 +
## hospitaldischargeyear + dialysis + aids + hepaticfailure +
## diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer +
## thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline,
## family = "binomial", data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.8380 -0.5240 -0.3328 -0.1673 3.4801
##
## Coefficients:
## Estimate Std. Error z value
## (Intercept) -3.978119 0.053948 -73.740
## as.factor(SOFA_Positive)TRUE 2.020614 0.018376 109.959
## age_Ranges(25,35] 0.215132 0.049528 4.344
## age_Ranges(35,45] 0.395554 0.045716 8.652
## age_Ranges(45,55] 0.689357 0.042315 16.291
## age_Ranges(55,65] 0.916742 0.041492 22.095
## age_Ranges(65,75] 1.130514 0.041313 27.365
## age_Ranges(75,85] 1.369151 0.041246 33.195
## age_Ranges(85,100] 1.562525 0.042060 37.150
## gender2Female -0.019092 0.009065 -2.106
## gender2Other/Unknown 1.934512 0.186694 10.362
## ethnicity2African American -0.033650 0.014909 -2.257
## ethnicity2Hispanic 0.047706 0.021550 2.214
## ethnicity2Asian 0.094731 0.038058 2.489
## ethnicity2Native American 0.294545 0.049580 5.941
## ethnicity2Other/Unknown 0.174577 0.019311 9.040
## BMI_Ranges(18.5,25] -0.313238 0.018909 -16.566
## BMI_Ranges(25,35] -0.477467 0.018647 -25.605
## BMI_Ranges(35,200] -0.389262 0.020822 -18.695
## BMI_RangesOther/Unknown 0.031327 0.027394 1.144
## icu_admit_source2OR/Proc Area -1.449279 0.017681 -81.968
## icu_admit_source2Direct Admit -0.311429 0.015879 -19.613
## icu_admit_source2Emergency Department -0.424613 0.010937 -38.825
## icu_admit_source2Other -0.085987 0.041144 -2.090
## icu_admit_source2Step-Down Unit 0.146360 0.025244 5.798
## hospital_teaching_statusf -0.037912 0.032651 -1.161
## hospital_teaching_statust -0.152785 0.033018 -4.627
## hospital_size<100 -0.492326 0.036909 -13.339
## hospital_size100-249 -0.032021 0.025680 -1.247
## hospital_size250-500 0.069264 0.025923 2.672
## hospital_size>500 0.215502 0.024158 8.920
## physicianSpeciality2Speciality-Other -0.302475 0.010021 -30.183
## hospitaldischargeyear2011 -0.034288 0.017083 -2.007
## hospitaldischargeyear2012 -0.063331 0.016481 -3.843
## hospitaldischargeyear2013 -0.091968 0.016212 -5.673
## hospitaldischargeyear2014 -0.136227 0.016154 -8.433
## hospitaldischargeyear2015-16 -0.122819 0.015973 -7.689
## dialysis1 0.417044 0.022762 18.322
## aids1 0.475890 0.118844 4.004
## hepaticfailureTRUE 0.558113 0.024573 22.713
## diabetes1 -0.308962 0.011711 -26.381
## immunosuppression1 0.344634 0.025615 13.454
## leukemia1 0.393989 0.040016 9.846
## lymphoma1 0.247094 0.057337 4.310
## metastaticcancer1 0.684668 0.026839 25.510
## thrombolytics1 0.243885 0.035466 6.877
## sofa_respiration_baseline2TRUE 0.115258 0.010233 11.263
## cardiovascular_baseline1 0.057819 0.010430 5.544
## Pr(>|z|)
## (Intercept) < 2e-16 ***
## as.factor(SOFA_Positive)TRUE < 2e-16 ***
## age_Ranges(25,35] 1.40e-05 ***
## age_Ranges(35,45] < 2e-16 ***
## age_Ranges(45,55] < 2e-16 ***
## age_Ranges(55,65] < 2e-16 ***
## age_Ranges(65,75] < 2e-16 ***
## age_Ranges(75,85] < 2e-16 ***
## age_Ranges(85,100] < 2e-16 ***
## gender2Female 0.035194 *
## gender2Other/Unknown < 2e-16 ***
## ethnicity2African American 0.024005 *
## ethnicity2Hispanic 0.026843 *
## ethnicity2Asian 0.012805 *
## ethnicity2Native American 2.84e-09 ***
## ethnicity2Other/Unknown < 2e-16 ***
## BMI_Ranges(18.5,25] < 2e-16 ***
## BMI_Ranges(25,35] < 2e-16 ***
## BMI_Ranges(35,200] < 2e-16 ***
## BMI_RangesOther/Unknown 0.252815
## icu_admit_source2OR/Proc Area < 2e-16 ***
## icu_admit_source2Direct Admit < 2e-16 ***
## icu_admit_source2Emergency Department < 2e-16 ***
## icu_admit_source2Other 0.036629 *
## icu_admit_source2Step-Down Unit 6.72e-09 ***
## hospital_teaching_statusf 0.245594
## hospital_teaching_statust 3.70e-06 ***
## hospital_size<100 < 2e-16 ***
## hospital_size100-249 0.212422
## hospital_size250-500 0.007543 **
## hospital_size>500 < 2e-16 ***
## physicianSpeciality2Speciality-Other < 2e-16 ***
## hospitaldischargeyear2011 0.044739 *
## hospitaldischargeyear2012 0.000122 ***
## hospitaldischargeyear2013 1.41e-08 ***
## hospitaldischargeyear2014 < 2e-16 ***
## hospitaldischargeyear2015-16 1.48e-14 ***
## dialysis1 < 2e-16 ***
## aids1 6.22e-05 ***
## hepaticfailureTRUE < 2e-16 ***
## diabetes1 < 2e-16 ***
## immunosuppression1 < 2e-16 ***
## leukemia1 < 2e-16 ***
## lymphoma1 1.64e-05 ***
## metastaticcancer1 < 2e-16 ***
## thrombolytics1 6.13e-12 ***
## sofa_respiration_baseline2TRUE < 2e-16 ***
## cardiovascular_baseline1 2.96e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 399603 on 638756 degrees of freedom
## Residual deviance: 350403 on 638709 degrees of freedom
## AIC: 350499
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$SOFA2ADJHospMortPred <- predict(SOFA2_ADJ_Hosp_Mort_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
SOFA2ADJMort.Pred <- prediction(ssd_incl_te$SOFA2ADJHospMortPred, ssd_incl_te$hospital_mortality_ultimate)
SOFA2ADJMort.Perf <- performance(SOFA2ADJMort.Pred, "tpr", "fpr")
plot(SOFA2ADJMort.Perf, main = "SOFA Positive Adjusted
Mortality Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SOFA2ADJMort.Pred,"auc")@y.values[[1]],3))) 
performance(SOFA2ADJMort.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.7592311
##
##
## Slot "alpha.values":
## list()SOFA2ADJMort.Pred.roc <- roc(hospital_mortality_ultimate~ SOFA2ADJHospMortPred,data=ssd_incl_te)
ci(SOFA2ADJMort.Pred.roc, conf.level=0.99)## 99% CI: 0.7557-0.7627 (DeLong)ggplot(calibration(as.factor(hospital_mortality_ultimate==0)~SOFA2ADJHospMortPred, data = ssd_incl_te))+ggtitle("Calibration of ADJ Mortality SOFA Positive Prediction")## Warning: Removed 2 rows containing missing values (geom_errorbar).
qplot(SOFA2ADJHospMortPred, data = ssd_incl_te)+ggtitle("Histogram of ADJ Mortality SOFA Positive Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
SOFA score positive without baseline SOFA
SOFA3_ADJ_Hosp_Mort_tr<-glm(hospital_mortality_ultimate ~ as.factor(SOFA_Positive2) + age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status + hospital_size + physicianSpeciality2 + hospitaldischargeyear + dialysis + aids + hepaticfailure + diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer + thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline, data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SOFA3_ADJ_Hosp_Mort_tr)
#sjt.glm(SOFA3_ADJ_Hosp_Mort_tr)
#drop1(SOFA3_ADJ_Hosp_Mort_tr,test="Chisq")
summary(SOFA3_ADJ_Hosp_Mort_tr)##
## Call:
## glm(formula = hospital_mortality_ultimate ~ as.factor(SOFA_Positive2) +
## age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 +
## hospital_teaching_status + hospital_size + physicianSpeciality2 +
## hospitaldischargeyear + dialysis + aids + hepaticfailure +
## diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer +
## thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline,
## family = "binomial", data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.8265 -0.5241 -0.3413 -0.1648 3.4979
##
## Coefficients:
## Estimate Std. Error z value
## (Intercept) -4.022666 0.054342 -74.025
## as.factor(SOFA_Positive2)TRUE 2.070136 0.019691 105.128
## age_Ranges(25,35] 0.206791 0.049510 4.177
## age_Ranges(35,45] 0.386802 0.045701 8.464
## age_Ranges(45,55] 0.685480 0.042302 16.205
## age_Ranges(55,65] 0.915737 0.041479 22.077
## age_Ranges(65,75] 1.133289 0.041300 27.440
## age_Ranges(75,85] 1.375282 0.041235 33.352
## age_Ranges(85,100] 1.571159 0.042050 37.364
## gender2Female -0.022891 0.009053 -2.529
## gender2Other/Unknown 1.909668 0.186607 10.234
## ethnicity2African American -0.037713 0.014880 -2.535
## ethnicity2Hispanic 0.039776 0.021506 1.850
## ethnicity2Asian 0.096467 0.037981 2.540
## ethnicity2Native American 0.307064 0.049439 6.211
## ethnicity2Other/Unknown 0.173564 0.019283 9.001
## BMI_Ranges(18.5,25] -0.314244 0.018874 -16.650
## BMI_Ranges(25,35] -0.477045 0.018613 -25.629
## BMI_Ranges(35,200] -0.390237 0.020781 -18.778
## BMI_RangesOther/Unknown 0.028400 0.027349 1.038
## icu_admit_source2OR/Proc Area -1.445876 0.017671 -81.821
## icu_admit_source2Direct Admit -0.311644 0.015853 -19.658
## icu_admit_source2Emergency Department -0.425477 0.010916 -38.977
## icu_admit_source2Other -0.076304 0.041097 -1.857
## icu_admit_source2Step-Down Unit 0.150637 0.025189 5.980
## hospital_teaching_statusf -0.039567 0.032606 -1.213
## hospital_teaching_statust -0.151906 0.032980 -4.606
## hospital_size<100 -0.498093 0.036872 -13.509
## hospital_size100-249 -0.035545 0.025642 -1.386
## hospital_size250-500 0.071683 0.025888 2.769
## hospital_size>500 0.214426 0.024128 8.887
## physicianSpeciality2Speciality-Other -0.301722 0.010010 -30.142
## hospitaldischargeyear2011 -0.034558 0.017062 -2.025
## hospitaldischargeyear2012 -0.064082 0.016461 -3.893
## hospitaldischargeyear2013 -0.096544 0.016190 -5.963
## hospitaldischargeyear2014 -0.139689 0.016131 -8.660
## hospitaldischargeyear2015-16 -0.126314 0.015951 -7.919
## dialysis1 0.094191 0.022225 4.238
## aids1 0.495812 0.118478 4.185
## hepaticfailureTRUE 0.553304 0.024479 22.603
## diabetes1 -0.305693 0.011685 -26.162
## immunosuppression1 0.340377 0.025563 13.315
## leukemia1 0.405643 0.039939 10.156
## lymphoma1 0.252952 0.057272 4.417
## metastaticcancer1 0.684713 0.026800 25.549
## thrombolytics1 0.250331 0.035468 7.058
## sofa_respiration_baseline2TRUE 0.075186 0.010211 7.363
## cardiovascular_baseline1 0.058011 0.010409 5.573
## Pr(>|z|)
## (Intercept) < 2e-16 ***
## as.factor(SOFA_Positive2)TRUE < 2e-16 ***
## age_Ranges(25,35] 2.96e-05 ***
## age_Ranges(35,45] < 2e-16 ***
## age_Ranges(45,55] < 2e-16 ***
## age_Ranges(55,65] < 2e-16 ***
## age_Ranges(65,75] < 2e-16 ***
## age_Ranges(75,85] < 2e-16 ***
## age_Ranges(85,100] < 2e-16 ***
## gender2Female 0.01145 *
## gender2Other/Unknown < 2e-16 ***
## ethnicity2African American 0.01126 *
## ethnicity2Hispanic 0.06438 .
## ethnicity2Asian 0.01109 *
## ethnicity2Native American 5.27e-10 ***
## ethnicity2Other/Unknown < 2e-16 ***
## BMI_Ranges(18.5,25] < 2e-16 ***
## BMI_Ranges(25,35] < 2e-16 ***
## BMI_Ranges(35,200] < 2e-16 ***
## BMI_RangesOther/Unknown 0.29908
## icu_admit_source2OR/Proc Area < 2e-16 ***
## icu_admit_source2Direct Admit < 2e-16 ***
## icu_admit_source2Emergency Department < 2e-16 ***
## icu_admit_source2Other 0.06336 .
## icu_admit_source2Step-Down Unit 2.23e-09 ***
## hospital_teaching_statusf 0.22494
## hospital_teaching_statust 4.10e-06 ***
## hospital_size<100 < 2e-16 ***
## hospital_size100-249 0.16568
## hospital_size250-500 0.00562 **
## hospital_size>500 < 2e-16 ***
## physicianSpeciality2Speciality-Other < 2e-16 ***
## hospitaldischargeyear2011 0.04282 *
## hospitaldischargeyear2012 9.90e-05 ***
## hospitaldischargeyear2013 2.47e-09 ***
## hospitaldischargeyear2014 < 2e-16 ***
## hospitaldischargeyear2015-16 2.39e-15 ***
## dialysis1 2.25e-05 ***
## aids1 2.85e-05 ***
## hepaticfailureTRUE < 2e-16 ***
## diabetes1 < 2e-16 ***
## immunosuppression1 < 2e-16 ***
## leukemia1 < 2e-16 ***
## lymphoma1 1.00e-05 ***
## metastaticcancer1 < 2e-16 ***
## thrombolytics1 1.69e-12 ***
## sofa_respiration_baseline2TRUE 1.80e-13 ***
## cardiovascular_baseline1 2.50e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 399603 on 638756 degrees of freedom
## Residual deviance: 351548 on 638709 degrees of freedom
## AIC: 351644
##
## Number of Fisher Scoring iterations: 7ssd_incl_te$SOFA3ADJHospMortPred <- predict(SOFA3_ADJ_Hosp_Mort_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
SOFA3ADJMort.Pred <- prediction(ssd_incl_te$SOFA3ADJHospMortPred, ssd_incl_te$hospital_mortality_ultimate)
SOFA3ADJMort.Perf <- performance(SOFA3ADJMort.Pred, "tpr", "fpr")
plot(SOFA3ADJMort.Perf, main = "SOFA Positive w/o Baseline Adjusted
Mortality Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SOFA3ADJMort.Pred,"auc")@y.values[[1]],3))) 
performance(SOFA3ADJMort.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.7562943
##
##
## Slot "alpha.values":
## list()SOFA3ADJMort.Pred.roc <- roc(hospital_mortality_ultimate~ SOFA3ADJHospMortPred,data=ssd_incl_te)
ci(SOFA3ADJMort.Pred.roc, conf.level=0.99)## 99% CI: 0.7528-0.7598 (DeLong)ggplot(calibration(as.factor(hospital_mortality_ultimate==0)~SOFA3ADJHospMortPred, data = ssd_incl_te))+ggtitle("Calibration of ADJ Mortality SOFA Positive w/o Baseline Prediction")## Warning: Removed 2 rows containing missing values (geom_errorbar).
qplot(SOFA3ADJHospMortPred, data = ssd_incl_te)+ggtitle("Histogram of ADJ Mortality SOFA Positive w/o Baseline Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
qSOFA1_ADJ_Hosp_Mort_tr<-glm(hospital_mortality_ultimate ~ as.factor(qSOFA_total) + age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status + hospital_size + physicianSpeciality2 + hospitaldischargeyear + dialysis + aids + hepaticfailure + diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer + thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline, data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(qSOFA1_ADJ_Hosp_Mort_tr)
#sjt.glm(qSOFA1_ADJ_Hosp_Mort_tr)
#drop1(qSOFA1_ADJ_Hosp_Mort_tr,test="Chisq")
summary(qSOFA1_ADJ_Hosp_Mort_tr)##
## Call:
## glm(formula = hospital_mortality_ultimate ~ as.factor(qSOFA_total) +
## age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 +
## hospital_teaching_status + hospital_size + physicianSpeciality2 +
## hospitaldischargeyear + dialysis + aids + hepaticfailure +
## diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer +
## thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline,
## family = "binomial", data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.0781 -0.4725 -0.3128 -0.1937 3.5246
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.48635 0.06848 -65.509 < 2e-16
## as.factor(qSOFA_total)1 1.00808 0.04734 21.293 < 2e-16
## as.factor(qSOFA_total)2 1.94445 0.04577 42.483 < 2e-16
## as.factor(qSOFA_total)3 2.95871 0.04575 64.676 < 2e-16
## age_Ranges(25,35] 0.24743 0.04965 4.984 6.24e-07
## age_Ranges(35,45] 0.42222 0.04584 9.210 < 2e-16
## age_Ranges(45,55] 0.73252 0.04242 17.267 < 2e-16
## age_Ranges(55,65] 0.98791 0.04159 23.752 < 2e-16
## age_Ranges(65,75] 1.22975 0.04141 29.698 < 2e-16
## age_Ranges(75,85] 1.49355 0.04134 36.125 < 2e-16
## age_Ranges(85,100] 1.66198 0.04219 39.393 < 2e-16
## gender2Female -0.09968 0.00918 -10.858 < 2e-16
## gender2Other/Unknown 1.85305 0.18824 9.844 < 2e-16
## ethnicity2African American 0.03574 0.01514 2.360 0.018255
## ethnicity2Hispanic 0.11388 0.02188 5.205 1.94e-07
## ethnicity2Asian 0.14790 0.03872 3.820 0.000134
## ethnicity2Native American 0.31628 0.05041 6.274 3.51e-10
## ethnicity2Other/Unknown 0.23091 0.01960 11.781 < 2e-16
## BMI_Ranges(18.5,25] -0.25980 0.01918 -13.548 < 2e-16
## BMI_Ranges(25,35] -0.37658 0.01892 -19.909 < 2e-16
## BMI_Ranges(35,200] -0.26780 0.02112 -12.680 < 2e-16
## BMI_RangesOther/Unknown 0.11647 0.02776 4.196 2.72e-05
## icu_admit_source2OR/Proc Area -1.36067 0.01785 -76.233 < 2e-16
## icu_admit_source2Direct Admit -0.24365 0.01612 -15.119 < 2e-16
## icu_admit_source2Emergency Department -0.39992 0.01111 -35.980 < 2e-16
## icu_admit_source2Other -0.10582 0.04178 -2.533 0.011308
## icu_admit_source2Step-Down Unit 0.14124 0.02571 5.493 3.94e-08
## hospital_teaching_statusf -0.22706 0.03302 -6.878 6.09e-12
## hospital_teaching_statust -0.35201 0.03319 -10.606 < 2e-16
## hospital_size<100 -0.25685 0.03725 -6.896 5.35e-12
## hospital_size100-249 0.18021 0.02594 6.948 3.70e-12
## hospital_size250-500 0.25599 0.02618 9.778 < 2e-16
## hospital_size>500 0.38362 0.02426 15.814 < 2e-16
## physicianSpeciality2Speciality-Other -0.25256 0.01014 -24.904 < 2e-16
## hospitaldischargeyear2011 -0.08942 0.01737 -5.147 2.65e-07
## hospitaldischargeyear2012 -0.16375 0.01675 -9.777 < 2e-16
## hospitaldischargeyear2013 -0.20339 0.01646 -12.355 < 2e-16
## hospitaldischargeyear2014 -0.23849 0.01640 -14.542 < 2e-16
## hospitaldischargeyear2015-16 -0.24052 0.01622 -14.824 < 2e-16
## dialysis1 0.30372 0.02307 13.166 < 2e-16
## aids1 0.47169 0.12083 3.904 9.47e-05
## hepaticfailureTRUE 0.66597 0.02526 26.366 < 2e-16
## diabetes1 -0.26099 0.01188 -21.968 < 2e-16
## immunosuppression1 0.42742 0.02603 16.422 < 2e-16
## leukemia1 0.51659 0.04108 12.575 < 2e-16
## lymphoma1 0.29826 0.05838 5.109 3.24e-07
## metastaticcancer1 0.70288 0.02718 25.858 < 2e-16
## thrombolytics1 0.15957 0.03535 4.514 6.35e-06
## sofa_respiration_baseline2TRUE 0.02806 0.01036 2.708 0.006764
## cardiovascular_baseline1 0.11607 0.01059 10.961 < 2e-16
##
## (Intercept) ***
## as.factor(qSOFA_total)1 ***
## as.factor(qSOFA_total)2 ***
## as.factor(qSOFA_total)3 ***
## age_Ranges(25,35] ***
## age_Ranges(35,45] ***
## age_Ranges(45,55] ***
## age_Ranges(55,65] ***
## age_Ranges(65,75] ***
## age_Ranges(75,85] ***
## age_Ranges(85,100] ***
## gender2Female ***
## gender2Other/Unknown ***
## ethnicity2African American *
## ethnicity2Hispanic ***
## ethnicity2Asian ***
## ethnicity2Native American ***
## ethnicity2Other/Unknown ***
## BMI_Ranges(18.5,25] ***
## BMI_Ranges(25,35] ***
## BMI_Ranges(35,200] ***
## BMI_RangesOther/Unknown ***
## icu_admit_source2OR/Proc Area ***
## icu_admit_source2Direct Admit ***
## icu_admit_source2Emergency Department ***
## icu_admit_source2Other *
## icu_admit_source2Step-Down Unit ***
## hospital_teaching_statusf ***
## hospital_teaching_statust ***
## hospital_size<100 ***
## hospital_size100-249 ***
## hospital_size250-500 ***
## hospital_size>500 ***
## physicianSpeciality2Speciality-Other ***
## hospitaldischargeyear2011 ***
## hospitaldischargeyear2012 ***
## hospitaldischargeyear2013 ***
## hospitaldischargeyear2014 ***
## hospitaldischargeyear2015-16 ***
## dialysis1 ***
## aids1 ***
## hepaticfailureTRUE ***
## diabetes1 ***
## immunosuppression1 ***
## leukemia1 ***
## lymphoma1 ***
## metastaticcancer1 ***
## thrombolytics1 ***
## sofa_respiration_baseline2TRUE **
## cardiovascular_baseline1 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 399603 on 638756 degrees of freedom
## Residual deviance: 343488 on 638707 degrees of freedom
## AIC: 343588
##
## Number of Fisher Scoring iterations: 7ssd_incl_te$qSOFA1ADJHospMortPred <- predict(qSOFA1_ADJ_Hosp_Mort_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
qSOFA1ADJMort.Pred <- prediction(ssd_incl_te$qSOFA1ADJHospMortPred, ssd_incl_te$hospital_mortality_ultimate)
qSOFA1ADJMort.Perf <- performance(qSOFA1ADJMort.Pred, "tpr", "fpr")
plot(qSOFA1ADJMort.Perf, main = "qSOFA1 Continuous Adjusted
Mortality Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(qSOFA1ADJMort.Pred,"auc")@y.values[[1]],3))) 
performance(qSOFA1ADJMort.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.7777231
##
##
## Slot "alpha.values":
## list()qSOFA1ADJMort.Pred.roc <- roc(hospital_mortality_ultimate~ qSOFA1ADJHospMortPred,data=ssd_incl_te)
ci(qSOFA1ADJMort.Pred.roc, conf.level=0.99)## 99% CI: 0.7741-0.7814 (DeLong)ggplot(calibration(as.factor(hospital_mortality_ultimate==0)~qSOFA1ADJHospMortPred, data = ssd_incl_te))+ggtitle("Calibration of ADJ Mortality qSOFA Total Prediction")## Warning: Removed 1 rows containing missing values (geom_errorbar).
qplot(qSOFA1ADJHospMortPred, data = ssd_incl_te)+ggtitle("Histogram of ADJ Mortality qSOFA Total Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
qSOFA2_ADJ_Hosp_Mort_tr<-glm(hospital_mortality_ultimate ~ as.factor(qSOFA_Positive) + age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status + hospital_size + physicianSpeciality2 + hospitaldischargeyear + dialysis + aids + hepaticfailure + diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer + thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline, data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(qSOFA2_ADJ_Hosp_Mort_tr)
#sjt.glm(qSOFA2_ADJ_Hosp_Mort_tr)
#drop1(qSOFA2_ADJ_Hosp_Mort_tr,test="Chisq")
summary(qSOFA2_ADJ_Hosp_Mort_tr)##
## Call:
## glm(formula = hospital_mortality_ultimate ~ as.factor(qSOFA_Positive) +
## age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 +
## hospital_teaching_status + hospital_size + physicianSpeciality2 +
## hospitaldischargeyear + dialysis + aids + hepaticfailure +
## diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer +
## thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline,
## family = "binomial", data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.8052 -0.5088 -0.3339 -0.2045 3.4565
##
## Coefficients:
## Estimate Std. Error z value
## (Intercept) -3.508901 0.052607 -66.701
## as.factor(qSOFA_Positive)TRUE 1.525327 0.014401 105.917
## age_Ranges(25,35] 0.241662 0.049333 4.899
## age_Ranges(35,45] 0.420857 0.045539 9.242
## age_Ranges(45,55] 0.737753 0.042141 17.507
## age_Ranges(55,65] 1.000275 0.041316 24.211
## age_Ranges(65,75] 1.244254 0.041131 30.251
## age_Ranges(75,85] 1.521611 0.041065 37.054
## age_Ranges(85,100] 1.730355 0.041881 41.316
## gender2Female -0.093649 0.009044 -10.354
## gender2Other/Unknown 1.843265 0.184148 10.010
## ethnicity2African American 0.038999 0.014918 2.614
## ethnicity2Hispanic 0.106499 0.021534 4.946
## ethnicity2Asian 0.137830 0.038050 3.622
## ethnicity2Native American 0.367605 0.049623 7.408
## ethnicity2Other/Unknown 0.230829 0.019291 11.966
## BMI_Ranges(18.5,25] -0.291869 0.018827 -15.502
## BMI_Ranges(25,35] -0.432094 0.018573 -23.265
## BMI_Ranges(35,200] -0.312671 0.020749 -15.069
## BMI_RangesOther/Unknown 0.048488 0.027255 1.779
## icu_admit_source2OR/Proc Area -1.412684 0.017669 -79.954
## icu_admit_source2Direct Admit -0.302155 0.015838 -19.078
## icu_admit_source2Emergency Department -0.435392 0.010916 -39.887
## icu_admit_source2Other -0.093011 0.041049 -2.266
## icu_admit_source2Step-Down Unit 0.148979 0.025197 5.913
## hospital_teaching_statusf -0.211453 0.032528 -6.501
## hospital_teaching_statust -0.325831 0.032722 -9.957
## hospital_size<100 -0.347279 0.036784 -9.441
## hospital_size100-249 0.120466 0.025548 4.715
## hospital_size250-500 0.237521 0.025803 9.205
## hospital_size>500 0.364198 0.023914 15.229
## physicianSpeciality2Speciality-Other -0.330597 0.009956 -33.206
## hospitaldischargeyear2011 -0.072053 0.017091 -4.216
## hospitaldischargeyear2012 -0.140386 0.016480 -8.519
## hospitaldischargeyear2013 -0.195734 0.016207 -12.077
## hospitaldischargeyear2014 -0.230626 0.016150 -14.281
## hospitaldischargeyear2015-16 -0.210284 0.015972 -13.166
## dialysis1 0.324834 0.022633 14.352
## aids1 0.479190 0.118795 4.034
## hepaticfailureTRUE 0.705191 0.024767 28.473
## diabetes1 -0.262420 0.011702 -22.426
## immunosuppression1 0.381358 0.025520 14.943
## leukemia1 0.491629 0.040230 12.220
## lymphoma1 0.275756 0.057416 4.803
## metastaticcancer1 0.680467 0.026658 25.526
## thrombolytics1 0.054774 0.034907 1.569
## sofa_respiration_baseline2TRUE 0.049611 0.010198 4.865
## cardiovascular_baseline1 0.098528 0.010413 9.462
## Pr(>|z|)
## (Intercept) < 2e-16 ***
## as.factor(qSOFA_Positive)TRUE < 2e-16 ***
## age_Ranges(25,35] 9.65e-07 ***
## age_Ranges(35,45] < 2e-16 ***
## age_Ranges(45,55] < 2e-16 ***
## age_Ranges(55,65] < 2e-16 ***
## age_Ranges(65,75] < 2e-16 ***
## age_Ranges(75,85] < 2e-16 ***
## age_Ranges(85,100] < 2e-16 ***
## gender2Female < 2e-16 ***
## gender2Other/Unknown < 2e-16 ***
## ethnicity2African American 0.008944 **
## ethnicity2Hispanic 7.59e-07 ***
## ethnicity2Asian 0.000292 ***
## ethnicity2Native American 1.28e-13 ***
## ethnicity2Other/Unknown < 2e-16 ***
## BMI_Ranges(18.5,25] < 2e-16 ***
## BMI_Ranges(25,35] < 2e-16 ***
## BMI_Ranges(35,200] < 2e-16 ***
## BMI_RangesOther/Unknown 0.075230 .
## icu_admit_source2OR/Proc Area < 2e-16 ***
## icu_admit_source2Direct Admit < 2e-16 ***
## icu_admit_source2Emergency Department < 2e-16 ***
## icu_admit_source2Other 0.023460 *
## icu_admit_source2Step-Down Unit 3.37e-09 ***
## hospital_teaching_statusf 8.00e-11 ***
## hospital_teaching_statust < 2e-16 ***
## hospital_size<100 < 2e-16 ***
## hospital_size100-249 2.41e-06 ***
## hospital_size250-500 < 2e-16 ***
## hospital_size>500 < 2e-16 ***
## physicianSpeciality2Speciality-Other < 2e-16 ***
## hospitaldischargeyear2011 2.49e-05 ***
## hospitaldischargeyear2012 < 2e-16 ***
## hospitaldischargeyear2013 < 2e-16 ***
## hospitaldischargeyear2014 < 2e-16 ***
## hospitaldischargeyear2015-16 < 2e-16 ***
## dialysis1 < 2e-16 ***
## aids1 5.49e-05 ***
## hepaticfailureTRUE < 2e-16 ***
## diabetes1 < 2e-16 ***
## immunosuppression1 < 2e-16 ***
## leukemia1 < 2e-16 ***
## lymphoma1 1.57e-06 ***
## metastaticcancer1 < 2e-16 ***
## thrombolytics1 0.116617
## sofa_respiration_baseline2TRUE 1.15e-06 ***
## cardiovascular_baseline1 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 399603 on 638756 degrees of freedom
## Residual deviance: 355239 on 638709 degrees of freedom
## AIC: 355335
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$qSOFA2ADJHospMortPred <- predict(qSOFA2_ADJ_Hosp_Mort_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
qSOFA2ADJMort.Pred <- prediction(ssd_incl_te$qSOFA2ADJHospMortPred, ssd_incl_te$hospital_mortality_ultimate)
qSOFA2ADJMort.Perf <- performance(qSOFA2ADJMort.Pred, "tpr", "fpr")
plot(qSOFA2ADJMort.Perf, main = "qSOFA Positive Adjusted
Mortality Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(qSOFA2ADJMort.Pred,"auc")@y.values[[1]],3))) 
performance(qSOFA2ADJMort.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.7505584
##
##
## Slot "alpha.values":
## list()qSOFA2ADJMort.Pred.roc <- roc(hospital_mortality_ultimate~ qSOFA2ADJHospMortPred,data=ssd_incl_te)
ci(qSOFA2ADJMort.Pred.roc, conf.level=0.99)## 99% CI: 0.7468-0.7543 (DeLong)ggplot(calibration(as.factor(hospital_mortality_ultimate==0)~qSOFA2ADJHospMortPred, data = ssd_incl_te))+ggtitle("Calibration of ADJ Mortality qSOFA Positive Prediction")## Warning: Removed 2 rows containing missing values (geom_errorbar).
qplot(qSOFA2ADJHospMortPred, data = ssd_incl_te)+ggtitle("Histogram of ADJ Mortality qSOFA Positive Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
FuzzyLogic_ADJ_Hosp_Mort_tr<-glm(hospital_mortality_ultimate ~ as.factor(SepsisFuzzyLogicPositive) + age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status + hospital_size + physicianSpeciality2 + hospitaldischargeyear + dialysis + aids + hepaticfailure + diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer + thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline, data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(FuzzyLogic_ADJ_Hosp_Mort_tr)
#sjt.glm(FuzzyLogic_ADJ_Hosp_Mort_tr)
#drop1(FuzzyLogic_ADJ_Hosp_Mort_tr,test="Chisq")
summary(FuzzyLogic_ADJ_Hosp_Mort_tr)##
## Call:
## glm(formula = hospital_mortality_ultimate ~ as.factor(SepsisFuzzyLogicPositive) +
## age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 +
## hospital_teaching_status + hospital_size + physicianSpeciality2 +
## hospitaldischargeyear + dialysis + aids + hepaticfailure +
## diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer +
## thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline,
## family = "binomial", data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.8613 -0.5004 -0.2999 -0.1855 3.4055
##
## Coefficients:
## Estimate Std. Error z value
## (Intercept) -3.703509 0.052600 -70.409
## as.factor(SepsisFuzzyLogicPositive)TRUE 1.759015 0.012570 139.935
## age_Ranges(25,35] 0.263667 0.049480 5.329
## age_Ranges(35,45] 0.477884 0.045685 10.460
## age_Ranges(45,55] 0.800031 0.042270 18.927
## age_Ranges(55,65] 1.054713 0.041430 25.458
## age_Ranges(65,75] 1.297053 0.041250 31.444
## age_Ranges(75,85] 1.595510 0.041199 38.727
## age_Ranges(85,100] 1.846771 0.042060 43.907
## gender2Female -0.088610 0.009142 -9.692
## gender2Other/Unknown 1.881151 0.189779 9.912
## ethnicity2African American 0.063468 0.015096 4.204
## ethnicity2Hispanic 0.042223 0.021731 1.943
## ethnicity2Asian 0.168140 0.038579 4.358
## ethnicity2Native American 0.336567 0.050201 6.704
## ethnicity2Other/Unknown 0.169244 0.019481 8.688
## BMI_Ranges(18.5,25] -0.294102 0.019073 -15.420
## BMI_Ranges(25,35] -0.456729 0.018798 -24.297
## BMI_Ranges(35,200] -0.375163 0.020956 -17.903
## BMI_RangesOther/Unknown 0.130032 0.027747 4.686
## icu_admit_source2OR/Proc Area -1.469098 0.017785 -82.603
## icu_admit_source2Direct Admit -0.183843 0.016137 -11.392
## icu_admit_source2Emergency Department -0.440011 0.011052 -39.815
## icu_admit_source2Other 0.009575 0.041861 0.229
## icu_admit_source2Step-Down Unit 0.203620 0.025668 7.933
## hospital_teaching_statusf -0.074412 0.032934 -2.259
## hospital_teaching_statust -0.196285 0.033411 -5.875
## hospital_size<100 -0.541007 0.037110 -14.578
## hospital_size100-249 -0.035444 0.025884 -1.369
## hospital_size250-500 0.068296 0.026132 2.614
## hospital_size>500 0.220763 0.024403 9.047
## physicianSpeciality2Speciality-Other -0.254490 0.010172 -25.019
## hospitaldischargeyear2011 -0.040090 0.017261 -2.323
## hospitaldischargeyear2012 -0.067581 0.016650 -4.059
## hospitaldischargeyear2013 -0.111525 0.016367 -6.814
## hospitaldischargeyear2014 -0.143785 0.016309 -8.816
## hospitaldischargeyear2015-16 -0.129634 0.016130 -8.037
## dialysis1 0.338289 0.022950 14.740
## aids1 0.466865 0.119626 3.903
## hepaticfailureTRUE 0.574390 0.024879 23.087
## diabetes1 -0.144764 0.011815 -12.253
## immunosuppression1 0.295457 0.025719 11.488
## leukemia1 0.398376 0.040567 9.820
## lymphoma1 0.220802 0.057899 3.814
## metastaticcancer1 0.640238 0.026978 23.732
## thrombolytics1 0.191425 0.035568 5.382
## sofa_respiration_baseline2TRUE -0.027827 0.010317 -2.697
## cardiovascular_baseline1 0.113244 0.010540 10.744
## Pr(>|z|)
## (Intercept) < 2e-16 ***
## as.factor(SepsisFuzzyLogicPositive)TRUE < 2e-16 ***
## age_Ranges(25,35] 9.89e-08 ***
## age_Ranges(35,45] < 2e-16 ***
## age_Ranges(45,55] < 2e-16 ***
## age_Ranges(55,65] < 2e-16 ***
## age_Ranges(65,75] < 2e-16 ***
## age_Ranges(75,85] < 2e-16 ***
## age_Ranges(85,100] < 2e-16 ***
## gender2Female < 2e-16 ***
## gender2Other/Unknown < 2e-16 ***
## ethnicity2African American 2.62e-05 ***
## ethnicity2Hispanic 0.052014 .
## ethnicity2Asian 1.31e-05 ***
## ethnicity2Native American 2.02e-11 ***
## ethnicity2Other/Unknown < 2e-16 ***
## BMI_Ranges(18.5,25] < 2e-16 ***
## BMI_Ranges(25,35] < 2e-16 ***
## BMI_Ranges(35,200] < 2e-16 ***
## BMI_RangesOther/Unknown 2.78e-06 ***
## icu_admit_source2OR/Proc Area < 2e-16 ***
## icu_admit_source2Direct Admit < 2e-16 ***
## icu_admit_source2Emergency Department < 2e-16 ***
## icu_admit_source2Other 0.819081
## icu_admit_source2Step-Down Unit 2.14e-15 ***
## hospital_teaching_statusf 0.023857 *
## hospital_teaching_statust 4.23e-09 ***
## hospital_size<100 < 2e-16 ***
## hospital_size100-249 0.170899
## hospital_size250-500 0.008961 **
## hospital_size>500 < 2e-16 ***
## physicianSpeciality2Speciality-Other < 2e-16 ***
## hospitaldischargeyear2011 0.020203 *
## hospitaldischargeyear2012 4.93e-05 ***
## hospitaldischargeyear2013 9.49e-12 ***
## hospitaldischargeyear2014 < 2e-16 ***
## hospitaldischargeyear2015-16 9.23e-16 ***
## dialysis1 < 2e-16 ***
## aids1 9.51e-05 ***
## hepaticfailureTRUE < 2e-16 ***
## diabetes1 < 2e-16 ***
## immunosuppression1 < 2e-16 ***
## leukemia1 < 2e-16 ***
## lymphoma1 0.000137 ***
## metastaticcancer1 < 2e-16 ***
## thrombolytics1 7.37e-08 ***
## sofa_respiration_baseline2TRUE 0.006994 **
## cardiovascular_baseline1 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 399603 on 638756 degrees of freedom
## Residual deviance: 344313 on 638709 degrees of freedom
## AIC: 344409
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$FuzzyLogicADJHospMortPred <- predict(FuzzyLogic_ADJ_Hosp_Mort_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
FuzzyLogicADJMort.Pred <- prediction(ssd_incl_te$FuzzyLogicADJHospMortPred, ssd_incl_te$hospital_mortality_ultimate)
FuzzyLogicADJMort.Perf <- performance(FuzzyLogicADJMort.Pred, "tpr", "fpr")
plot(FuzzyLogicADJMort.Perf, main = "FuzzyLogic Positive Adjusted
Mortality Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(FuzzyLogicADJMort.Pred,"auc")@y.values[[1]],3))) 
performance(FuzzyLogicADJMort.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.7767738
##
##
## Slot "alpha.values":
## list()FuzzyLogicADJMort.Pred.roc <- roc(hospital_mortality_ultimate~ FuzzyLogicADJHospMortPred,data=ssd_incl_te)
ci(FuzzyLogicADJMort.Pred.roc, conf.level=0.99)## 99% CI: 0.7733-0.7803 (DeLong)ggplot(calibration(as.factor(hospital_mortality_ultimate==0)~FuzzyLogicADJHospMortPred, data = ssd_incl_te))+ggtitle("Calibration of ADJ Mortality FuzzyLogic Positive Prediction")## Warning: Removed 1 rows containing missing values (geom_errorbar).
qplot(FuzzyLogicADJHospMortPred, data = ssd_incl_te)+ggtitle("Histogram of ADJ Mortality FuzzyLogic Positive Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
SIRS1_Crude_Hosp_Mort_tr<-glm(hospital_mortality_ultimate ~ as.factor(SIRS_total), data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SIRS1_Crude_Hosp_Mort_tr)
#sjt.glm(SIRS1_Crude_Hosp_Mort_tr)
#drop1(SIRS1_Crude_Hosp_Mort_tr,test="Chisq")
summary(SIRS1_Crude_Hosp_Mort_tr)##
## Call:
## glm(formula = hospital_mortality_ultimate ~ as.factor(SIRS_total),
## family = "binomial", data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.7314 -0.5259 -0.3661 -0.2475 2.8642
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.08504 0.04215 -96.91 <2e-16 ***
## as.factor(SIRS_total)1 0.61417 0.04544 13.52 <2e-16 ***
## as.factor(SIRS_total)2 1.41584 0.04302 32.91 <2e-16 ***
## as.factor(SIRS_total)3 2.17657 0.04271 50.96 <2e-16 ***
## as.factor(SIRS_total)4 2.90312 0.04303 67.47 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 399603 on 638756 degrees of freedom
## Residual deviance: 370766 on 638752 degrees of freedom
## AIC: 370776
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$SIRS1CrudeHospMortPred <- predict(SIRS1_Crude_Hosp_Mort_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
SIRS1CrudeMort.Pred <- prediction(ssd_incl_te$SIRS1CrudeHospMortPred, ssd_incl_te$hospital_mortality_ultimate)
SIRS1CrudeMort.Perf <- performance(SIRS1CrudeMort.Pred, "tpr", "fpr")
plot(SIRS1CrudeMort.Perf, main = "SIRS Continuous Crude
Mortality Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SIRS1CrudeMort.Pred,"auc")@y.values[[1]],3))) 
performance(SIRS1CrudeMort.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.6959156
##
##
## Slot "alpha.values":
## list()SIRS1CrudeMort.Pred.roc <- roc(hospital_mortality_ultimate~ SIRS1CrudeHospMortPred,data=ssd_incl_te)
ci(SIRS1CrudeMort.Pred.roc, conf.level=0.99)## 99% CI: 0.6918-0.7 (DeLong)ggplot(calibration(as.factor(hospital_mortality_ultimate==0)~SIRS1CrudeHospMortPred, data = ssd_incl_te))+ggtitle("Calibration of Crude Mortality SIRS Total Prediction")## Warning: Removed 8 rows containing missing values (geom_errorbar).
qplot(SIRS1CrudeHospMortPred, data = ssd_incl_te)+ggtitle("Histogram of Crude Mortality SIRS Total Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
SIRS2_Crude_Hosp_Mort_tr<-glm(hospital_mortality_ultimate ~ as.factor(SIRS_Positive), data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SIRS2_Crude_Hosp_Mort_tr)
#sjt.glm(SIRS2_Crude_Hosp_Mort_tr)
#drop1(SIRS2_Crude_Hosp_Mort_tr,test="Chisq")
summary(SIRS2_Crude_Hosp_Mort_tr)##
## Call:
## glm(formula = hospital_mortality_ultimate ~ as.factor(SIRS_Positive),
## family = "binomial", data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.4961 -0.4961 -0.4961 -0.2344 2.6865
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -3.58127 0.01573 -227.73 <2e-16 ***
## as.factor(SIRS_Positive)TRUE 1.54841 0.01635 94.68 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 399603 on 638756 degrees of freedom
## Residual deviance: 386134 on 638755 degrees of freedom
## AIC: 386138
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$SIRS2CrudeHospMortPred <- predict(SIRS2_Crude_Hosp_Mort_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
SIRS2CrudeMort.Pred <- prediction(ssd_incl_te$SIRS2CrudeHospMortPred, ssd_incl_te$hospital_mortality_ultimate)
SIRS2CrudeMort.Perf <- performance(SIRS2CrudeMort.Pred, "tpr", "fpr")
plot(SIRS2CrudeMort.Perf, main = "SIRS Positive Crude
Mortality Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SIRS2CrudeMort.Pred,"auc")@y.values[[1]],3))) 
performance(SIRS2CrudeMort.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.5932939
##
##
## Slot "alpha.values":
## list()SIRS2CrudeMort.Pred.roc <- roc(hospital_mortality_ultimate~ SIRS2CrudeHospMortPred,data=ssd_incl_te)
ci(SIRS2CrudeMort.Pred.roc, conf.level=0.99)## 99% CI: 0.591-0.5956 (DeLong)ggplot(calibration(as.factor(hospital_mortality_ultimate==0)~SIRS2CrudeHospMortPred, data = ssd_incl_te))+ggtitle("Calibration of Crude Mortality SIRS Positive Prediction")## Warning: Removed 9 rows containing missing values (geom_errorbar).
qplot(SIRS2CrudeHospMortPred, data = ssd_incl_te)+ggtitle("Histogram of Crude Mortality SIRS Positive Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
SOFA1_Crude_Hosp_Mort_tr<-glm(hospital_mortality_ultimate ~ as.factor(SOFA_Change), data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SOFA1_Crude_Hosp_Mort_tr)
#sjt.glm(SOFA1_Crude_Hosp_Mort_tr)
#drop1(SOFA1_Crude_Hosp_Mort_tr,test="Chisq")
summary(SOFA1_Crude_Hosp_Mort_tr)##
## Call:
## glm(formula = hospital_mortality_ultimate ~ as.factor(SOFA_Change),
## family = "binomial", data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.9792 -0.4160 -0.2553 -0.1955 3.0374
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.60300 0.04361 -105.54 <2e-16 ***
## as.factor(SOFA_Change) 1 0.65495 0.04767 13.74 <2e-16 ***
## as.factor(SOFA_Change) 2 1.19523 0.04735 25.24 <2e-16 ***
## as.factor(SOFA_Change) 3 1.77503 0.04620 38.42 <2e-16 ***
## as.factor(SOFA_Change) 4 2.19953 0.04568 48.15 <2e-16 ***
## as.factor(SOFA_Change) 5 2.59747 0.04553 57.05 <2e-16 ***
## as.factor(SOFA_Change) 6 2.82348 0.04590 61.52 <2e-16 ***
## as.factor(SOFA_Change) 7 3.28928 0.04577 71.87 <2e-16 ***
## as.factor(SOFA_Change) 8 3.52648 0.04639 76.02 <2e-16 ***
## as.factor(SOFA_Change) 9 3.81251 0.04714 80.88 <2e-16 ***
## as.factor(SOFA_Change)10 4.07496 0.04821 84.52 <2e-16 ***
## as.factor(SOFA_Change)11 4.46872 0.04968 89.95 <2e-16 ***
## as.factor(SOFA_Change)12 4.66489 0.05261 88.66 <2e-16 ***
## as.factor(SOFA_Change)13 4.97242 0.05686 87.46 <2e-16 ***
## as.factor(SOFA_Change)14 5.19252 0.06406 81.05 <2e-16 ***
## as.factor(SOFA_Change)15 5.49670 0.07577 72.54 <2e-16 ***
## as.factor(SOFA_Change)16 5.81940 0.09627 60.45 <2e-16 ***
## as.factor(SOFA_Change)17 6.17905 0.14112 43.79 <2e-16 ***
## as.factor(SOFA_Change)[18,23] 6.40953 0.15064 42.55 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 399603 on 638756 degrees of freedom
## Residual deviance: 322950 on 638738 degrees of freedom
## AIC: 322988
##
## Number of Fisher Scoring iterations: 7ssd_incl_te$SOFA1CrudeHospMortPred <- predict(SOFA1_Crude_Hosp_Mort_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
SOFA1CrudeMort.Pred <- prediction(ssd_incl_te$SOFA1CrudeHospMortPred, ssd_incl_te$hospital_mortality_ultimate)
SOFA1CrudeMort.Perf <- performance(SOFA1CrudeMort.Pred, "tpr", "fpr")
plot(SOFA1CrudeMort.Perf, main = "SOFA Continuous Crude Mortality Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SOFA1CrudeMort.Pred,"auc")@y.values[[1]],3))) 
performance(SOFA1CrudeMort.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.8037549
##
##
## Slot "alpha.values":
## list()SOFA1CrudeMort.Pred.roc <- roc(hospital_mortality_ultimate~ SOFA1CrudeHospMortPred,data=ssd_incl_te)
ci(SOFA1CrudeMort.Pred.roc, conf.level=0.99)## 99% CI: 0.8001-0.8074 (DeLong)ggplot(calibration(as.factor(hospital_mortality_ultimate==0)~SOFA1CrudeHospMortPred, data = ssd_incl_te))+ggtitle("Calibration of Crude Mortality SOFA Total Prediction")## Warning: Removed 1 rows containing missing values (geom_errorbar).
qplot(SOFA1CrudeHospMortPred, data = ssd_incl_te)+ggtitle("Histogram of Crude Mortality SOFA Total Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
SOFA2_Crude_Hosp_Mort_tr<-glm(hospital_mortality_ultimate ~ as.factor(SOFA_Positive), data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SOFA2_Crude_Hosp_Mort_tr)
#sjt.glm(SOFA2_Crude_Hosp_Mort_tr)
#drop1(SOFA2_Crude_Hosp_Mort_tr,test="Chisq")
summary(SOFA2_Crude_Hosp_Mort_tr)##
## Call:
## glm(formula = hospital_mortality_ultimate ~ as.factor(SOFA_Positive),
## family = "binomial", data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.5273 -0.5273 -0.5273 -0.1825 2.8650
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.08741 0.01759 -232.4 <2e-16 ***
## as.factor(SOFA_Positive)TRUE 2.18450 0.01815 120.3 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 399603 on 638756 degrees of freedom
## Residual deviance: 372927 on 638755 degrees of freedom
## AIC: 372931
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$SOFA2CrudeHospMortPred <- predict(SOFA2_Crude_Hosp_Mort_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
SOFA2CrudeMort.Pred <- prediction(ssd_incl_te$SOFA2CrudeHospMortPred, ssd_incl_te$hospital_mortality_ultimate)
SOFA2CrudeMort.Perf <- performance(SOFA2CrudeMort.Pred, "tpr", "fpr")
plot(SOFA2CrudeMort.Perf, main = "SOFA Positive Crude
Mortality Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SOFA2CrudeMort.Pred,"auc")@y.values[[1]],3))) 
performance(SOFA2CrudeMort.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.640742
##
##
## Slot "alpha.values":
## list()SOFA2CrudeMort.Pred.roc <- roc(hospital_mortality_ultimate~ SOFA2CrudeHospMortPred,data=ssd_incl_te)
ci(SOFA2CrudeMort.Pred.roc, conf.level=0.99)## 99% CI: 0.6385-0.643 (DeLong)ggplot(calibration(as.factor(hospital_mortality_ultimate==0)~SOFA2CrudeHospMortPred, data = ssd_incl_te))+ggtitle("Calibration of Crude Mortality SOFA Positive Prediction")## Warning: Removed 9 rows containing missing values (geom_errorbar).
qplot(SOFA2CrudeHospMortPred, data = ssd_incl_te)+ggtitle("Histogram of Crude Mortality SOFA Positive Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
SOFA3_Crude_Hosp_Mort_tr<-glm(hospital_mortality_ultimate ~ as.factor(SOFA_Positive2), data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SOFA3_Crude_Hosp_Mort_tr)
#sjt.glm(SOFA3_Crude_Hosp_Mort_tr)
#drop1(SOFA3_Crude_Hosp_Mort_tr,test="Chisq")
summary(SOFA3_Crude_Hosp_Mort_tr)##
## Call:
## glm(formula = hospital_mortality_ultimate ~ as.factor(SOFA_Positive2),
## family = "binomial", data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.5221 -0.5221 -0.5221 -0.1746 2.8952
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.17576 0.01892 -220.7 <2e-16 ***
## as.factor(SOFA_Positive2)TRUE 2.25170 0.01944 115.8 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 399603 on 638756 degrees of freedom
## Residual deviance: 373781 on 638755 degrees of freedom
## AIC: 373785
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$SOFA3CrudeHospMortPred <- predict(SOFA3_Crude_Hosp_Mort_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
SOFA3CrudeMort.Pred <- prediction(ssd_incl_te$SOFA3CrudeHospMortPred, ssd_incl_te$hospital_mortality_ultimate)
SOFA3CrudeMort.Perf <- performance(SOFA3CrudeMort.Pred, "tpr", "fpr")
plot(SOFA3CrudeMort.Perf, main = "SOFA Positive w/o Baseline Crude
Mortality Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SOFA3CrudeMort.Pred,"auc")@y.values[[1]],3))) 
performance(SOFA3CrudeMort.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.6351032
##
##
## Slot "alpha.values":
## list()SOFA3CrudeMort.Pred.roc <- roc(hospital_mortality_ultimate~ SOFA3CrudeHospMortPred,data=ssd_incl_te)
ci(SOFA3CrudeMort.Pred.roc, conf.level=0.99)## 99% CI: 0.633-0.6372 (DeLong)ggplot(calibration(as.factor(hospital_mortality_ultimate==0)~SOFA3CrudeHospMortPred, data = ssd_incl_te))+ggtitle("Calibration of Crude Mortality SOFA Positive w/o Baseline Prediction")## Warning: Removed 9 rows containing missing values (geom_errorbar).
qplot(SOFA3CrudeHospMortPred, data = ssd_incl_te)+ggtitle("Histogram of Crude Mortality SOFA Positive w/o Baseline Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
qSOFA1_Crude_Hosp_Mort_tr<-glm(hospital_mortality_ultimate ~ as.factor(qSOFA_total), data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(qSOFA1_Crude_Hosp_Mort_tr)
#sjt.glm(qSOFA1_Crude_Hosp_Mort_tr)
#drop1(qSOFA1_Crude_Hosp_Mort_tr,test="Chisq")
summary(qSOFA1_Crude_Hosp_Mort_tr)##
## Call:
## glm(formula = hospital_mortality_ultimate ~ as.factor(qSOFA_total),
## family = "binomial", data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.6843 -0.4132 -0.4132 -0.2540 3.0033
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.49890 0.04501 -99.94 <2e-16 ***
## as.factor(qSOFA_total)1 1.08072 0.04716 22.91 <2e-16 ***
## as.factor(qSOFA_total)2 2.08091 0.04555 45.69 <2e-16 ***
## as.factor(qSOFA_total)3 3.16630 0.04545 69.67 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 399603 on 638756 degrees of freedom
## Residual deviance: 365260 on 638753 degrees of freedom
## AIC: 365268
##
## Number of Fisher Scoring iterations: 7ssd_incl_te$qSOFA1CrudeHospMortPred <- predict(qSOFA1_Crude_Hosp_Mort_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
qSOFA1CrudeMort.Pred <- prediction(ssd_incl_te$qSOFA1CrudeHospMortPred, ssd_incl_te$hospital_mortality_ultimate)
qSOFA1CrudeMort.Perf <- performance(qSOFA1CrudeMort.Pred, "tpr", "fpr")
plot(qSOFA1CrudeMort.Perf, main = "qSOFA1 Continuous Crude
Mortality Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(qSOFA1CrudeMort.Pred,"auc")@y.values[[1]],3))) 
performance(qSOFA1CrudeMort.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.708034
##
##
## Slot "alpha.values":
## list()qSOFA1CrudeMort.Pred.roc <- roc(hospital_mortality_ultimate~ qSOFA1CrudeHospMortPred,data=ssd_incl_te)
ci(qSOFA1CrudeMort.Pred.roc, conf.level=0.99)## 99% CI: 0.7042-0.7118 (DeLong)ggplot(calibration(as.factor(hospital_mortality_ultimate==0)~qSOFA1CrudeHospMortPred, data = ssd_incl_te))+ggtitle("Calibration of Crude Mortality qSOFA Total Prediction")## Warning: Removed 9 rows containing missing values (geom_errorbar).
qplot(qSOFA1CrudeHospMortPred, data = ssd_incl_te)+ggtitle("Histogram of Crude Mortality qSOFA Total Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
qSOFA2_Crude_Hosp_Mort_tr<-glm(hospital_mortality_ultimate ~ as.factor(qSOFA_Positive), data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(qSOFA2_Crude_Hosp_Mort_tr)
#sjt.glm(qSOFA2_Crude_Hosp_Mort_tr)
#drop1(qSOFA2_Crude_Hosp_Mort_tr,test="Chisq")
summary(qSOFA2_Crude_Hosp_Mort_tr)##
## Call:
## glm(formula = hospital_mortality_ultimate ~ as.factor(qSOFA_Positive),
## family = "binomial", data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.5220 -0.5220 -0.5220 -0.2351 2.6843
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -3.57512 0.01341 -266.6 <2e-16 ***
## as.factor(qSOFA_Positive)TRUE 1.65074 0.01417 116.5 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 399603 on 638756 degrees of freedom
## Residual deviance: 379643 on 638755 degrees of freedom
## AIC: 379647
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$qSOFA2CrudeHospMortPred <- predict(qSOFA2_Crude_Hosp_Mort_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
qSOFA2CrudeMort.Pred <- prediction(ssd_incl_te$qSOFA2CrudeHospMortPred, ssd_incl_te$hospital_mortality_ultimate)
qSOFA2CrudeMort.Perf <- performance(qSOFA2CrudeMort.Pred, "tpr", "fpr")
plot(qSOFA2CrudeMort.Perf, main = "qSOFA Positive Crude
Mortality Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(qSOFA2CrudeMort.Pred,"auc")@y.values[[1]],3))) 
performance(qSOFA2CrudeMort.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.6290462
##
##
## Slot "alpha.values":
## list()qSOFA2CrudeMort.Pred.roc <- roc(hospital_mortality_ultimate~ qSOFA2CrudeHospMortPred,data=ssd_incl_te)
ci(qSOFA2CrudeMort.Pred.roc, conf.level=0.99)## 99% CI: 0.6264-0.6317 (DeLong)ggplot(calibration(as.factor(hospital_mortality_ultimate==0)~qSOFA2CrudeHospMortPred, data = ssd_incl_te))+ggtitle("Calibration of Crude Mortality qSOFA Positive Prediction")## Warning: Removed 9 rows containing missing values (geom_errorbar).
qplot(qSOFA2CrudeHospMortPred, data = ssd_incl_te)+ggtitle("Histogram of Crude Mortality qSOFA Positive Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
FuzzyLogic_Crude_Hosp_Mort_tr<-glm(hospital_mortality_ultimate ~ as.factor (SepsisFuzzyLogicPositive), data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(FuzzyLogic_Crude_Hosp_Mort_tr)
#sjt.glm(FuzzyLogic_Crude_Hosp_Mort_tr)
#drop1(FuzzyLogic_Crude_Hosp_Mort_tr,test="Chisq")
summary(FuzzyLogic_Crude_Hosp_Mort_tr)##
## Call:
## glm(formula = hospital_mortality_ultimate ~ as.factor(SepsisFuzzyLogicPositive),
## family = "binomial", data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.5675 -0.5675 -0.2384 -0.2384 2.6739
##
## Coefficients:
## Estimate Std. Error z value
## (Intercept) -3.54651 0.01131 -313.6
## as.factor(SepsisFuzzyLogicPositive)TRUE 1.80202 0.01226 147.0
## Pr(>|z|)
## (Intercept) <2e-16 ***
## as.factor(SepsisFuzzyLogicPositive)TRUE <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 399603 on 638756 degrees of freedom
## Residual deviance: 369149 on 638755 degrees of freedom
## AIC: 369153
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$FuzzyLogicCrudeHospMortPred <- predict(FuzzyLogic_Crude_Hosp_Mort_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
FuzzyLogicCrudeMort.Pred <- prediction(ssd_incl_te$FuzzyLogicCrudeHospMortPred, ssd_incl_te$hospital_mortality_ultimate)
FuzzyLogicCrudeMort.Perf <- performance(FuzzyLogicCrudeMort.Pred, "tpr", "fpr")
plot(FuzzyLogicCrudeMort.Perf, main = "FuzzyLogic Positive Crude
Mortality Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(FuzzyLogicCrudeMort.Pred,"auc")@y.values[[1]],3))) 
performance(FuzzyLogicCrudeMort.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.6734078
##
##
## Slot "alpha.values":
## list()FuzzyLogicCrudeMort.Pred.roc <- roc(hospital_mortality_ultimate~ FuzzyLogicCrudeHospMortPred,data=ssd_incl_te)
ci(FuzzyLogicCrudeMort.Pred.roc, conf.level=0.99)## 99% CI: 0.6704-0.6764 (DeLong)ggplot(calibration(as.factor(hospital_mortality_ultimate==0)~FuzzyLogicCrudeHospMortPred, data = ssd_incl_te))+ggtitle("Calibration of Crude Mortality FuzzyLogic Positive Prediction")## Warning: Removed 9 rows containing missing values (geom_errorbar).
qplot(FuzzyLogicCrudeHospMortPred, data = ssd_incl_te)+ggtitle("Histogram of Crude Mortality FuzzyLogic Positive Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
20 Setting up variables to analyze interactions
ssd_incl_te <- ssd_incl_te %>% mutate(hospital_mortality_ultimate2=hospital_mortality_ultimate)
ssd_incl_te <- ssd_incl_te %>% mutate(hospital_mortality_ultimate=as.logical(hospital_mortality_ultimate==1))
ssd_incl_te <- ssd_incl_te %>% mutate(SOFA2TruthMort=interaction(SOFA_Positive,hospital_mortality_ultimate))
ssd_incl_te <- ssd_incl_te %>% mutate(FuzzyLogicTruthMort=interaction(SepsisFuzzyLogicPositive, hospital_mortality_ultimate))
ssd_incl_te <- ssd_incl_te %>% mutate(qSOFA2TruthMort=interaction(qSOFA_Positive,hospital_mortality_ultimate))
ssd_incl_te <- ssd_incl_te %>% mutate(SIRS2TruthMort=interaction(SIRS_Positive,hospital_mortality_ultimate))vars5 <- c("age_Ranges", "gender2", "ethnicity2", "BMI_Ranges", "physicianSpeciality2", "icu_admit_source2", "icu_disch_location2", "hospitaldischargeyear", "dischargelocation", "dialysis", "aids", "hepaticfailure", "diabetes", "immunosuppression" , "leukemia", "lymphoma", "metastaticcancer", "thrombolytics", "sofa_respiration_baseline2", "sofa_liver_baseline2", "sofa_renal_baseline2", "cardiovascular_baseline", "group")
library(dplyr); library(Hmisc); library(ggplot2); library(sjPlot)
if(!("tableone" %in% rownames(installed.packages()))) {
install.packages("tableone")
}
library(tableone)
CreateTableOne(data=ssd_incl_te ,vars=vars5,strata="SIRS2TruthMort",test=FALSE, includeNA=TRUE
) %>% print(nonnormal= c("sofa_respiration_baseline2", "sofa_liver_baseline2", "sofa_renal_baseline2"),minMax=TRUE,
printToggle = FALSE,
showAllLevels = TRUE,
cramVars = "kon"
) %>%
{data.frame(
variable_name = gsub(" ", " ", rownames(.), fixed = TRUE), .,
row.names = NULL,
check.names = FALSE,
stringsAsFactors = FALSE)} %>%
knitr::kable(caption="SIRS Positive Hospital Mortality TRUE/FALSE")| variable_name | level | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE |
|---|---|---|---|---|---|
| n | 63427 | 184460 | 1792 | 24073 | |
| age_Ranges (%) | (0,25] | 1546 ( 2.4) | 7255 ( 3.9) | 1 ( 0.1) | 249 ( 1.0) |
| (25,35] | 2623 ( 4.1) | 10909 ( 5.9) | 14 ( 0.8) | 514 ( 2.1) | |
| (35,45] | 4182 ( 6.6) | 15147 ( 8.2) | 22 ( 1.2) | 977 ( 4.1) | |
| (45,55] | 9477 ( 14.9) | 28450 (15.4) | 136 ( 7.6) | 2466 (10.2) | |
| (55,65] | 13742 ( 21.7) | 38541 (20.9) | 263 (14.7) | 4558 (18.9) | |
| (65,75] | 14753 ( 23.3) | 39638 (21.5) | 426 (23.8) | 5789 (24.0) | |
| (75,85] | 12022 ( 19.0) | 30967 (16.8) | 584 (32.6) | 6049 (25.1) | |
| (85,100] | 5082 ( 8.0) | 13553 ( 7.3) | 346 (19.3) | 3471 (14.4) | |
| gender2 (%) | Male | 35515 ( 56.0) | 97773 (53.0) | 946 (52.8) | 12668 (52.6) |
| Female | 27900 ( 44.0) | 86658 (47.0) | 844 (47.1) | 11368 (47.2) | |
| Other/Unknown | 12 ( 0.0) | 29 ( 0.0) | 2 ( 0.1) | 37 ( 0.2) | |
| ethnicity2 (%) | Caucasian | 48120 ( 75.9) | 140669 (76.3) | 1397 (78.0) | 18502 (76.9) |
| African American | 7152 ( 11.3) | 21798 (11.8) | 175 ( 9.8) | 2604 (10.8) | |
| Hispanic | 2982 ( 4.7) | 8115 ( 4.4) | 96 ( 5.4) | 1092 ( 4.5) | |
| Asian | 822 ( 1.3) | 2349 ( 1.3) | 23 ( 1.3) | 339 ( 1.4) | |
| Native American | 452 ( 0.7) | 1382 ( 0.7) | 8 ( 0.4) | 170 ( 0.7) | |
| Other/Unknown | 3899 ( 6.1) | 10147 ( 5.5) | 93 ( 5.2) | 1366 ( 5.7) | |
| BMI_Ranges (%) | (0,18.5] | 2426 ( 3.8) | 9110 ( 4.9) | 109 ( 6.1) | 1803 ( 7.5) |
| (18.5,25] | 16805 ( 26.5) | 51771 (28.1) | 519 (29.0) | 7780 (32.3) | |
| (25,35] | 30888 ( 48.7) | 83875 (45.5) | 741 (41.4) | 9708 (40.3) | |
| (35,200] | 10559 ( 16.6) | 33940 (18.4) | 308 (17.2) | 3650 (15.2) | |
| Other/Unknown | 2749 ( 4.3) | 5764 ( 3.1) | 115 ( 6.4) | 1132 ( 4.7) | |
| physicianSpeciality2 (%) | Critical Care | 12577 ( 19.8) | 57963 (31.4) | 566 (31.6) | 9189 (38.2) |
| Speciality-Other | 50850 ( 80.2) | 126497 (68.6) | 1226 (68.4) | 14884 (61.8) | |
| icu_admit_source2 (%) | Floor | 8750 ( 13.8) | 30563 (16.6) | 479 (26.7) | 6642 (27.6) |
| OR/Proc Area | 11420 ( 18.0) | 39542 (21.4) | 139 ( 7.8) | 1830 ( 7.6) | |
| Direct Admit | 7814 ( 12.3) | 18602 (10.1) | 204 (11.4) | 2851 (11.8) | |
| Emergency Department | 34138 ( 53.8) | 90266 (48.9) | 896 (50.0) | 11374 (47.2) | |
| Other | 397 ( 0.6) | 1598 ( 0.9) | 19 ( 1.1) | 346 ( 1.4) | |
| Step-Down Unit | 908 ( 1.4) | 3889 ( 2.1) | 55 ( 3.1) | 1030 ( 4.3) | |
| icu_disch_location2 (%) | Floor | 46120 ( 72.7) | 146188 (79.3) | 667 (37.2) | 6444 (26.8) |
| Death | 0 ( 0.0) | 0 ( 0.0) | 1084 (60.5) | 17271 (71.7) | |
| Home | 11549 ( 18.2) | 15112 ( 8.2) | 2 ( 0.1) | 20 ( 0.1) | |
| SNF/Rehab | 848 ( 1.3) | 3408 ( 1.8) | 0 ( 0.0) | 2 ( 0.0) | |
| Other | 1727 ( 2.7) | 6959 ( 3.8) | 15 ( 0.8) | 104 ( 0.4) | |
| Other Hospital | 1363 ( 2.1) | 4775 ( 2.6) | 4 ( 0.2) | 14 ( 0.1) | |
| Step-Down Unit | 1820 ( 2.9) | 8018 ( 4.3) | 20 ( 1.1) | 218 ( 0.9) | |
| hospitaldischargeyear (%) | -2010 | 8716 ( 13.7) | 21266 (11.5) | 263 (14.7) | 3103 (12.9) |
| 2011 | 8885 ( 14.0) | 24249 (13.1) | 301 (16.8) | 3379 (14.0) | |
| 2012 | 10336 ( 16.3) | 30215 (16.4) | 273 (15.2) | 3986 (16.6) | |
| 2013 | 11374 ( 17.9) | 34135 (18.5) | 312 (17.4) | 4441 (18.4) | |
| 2014 | 12378 ( 19.5) | 36465 (19.8) | 312 (17.4) | 4396 (18.3) | |
| 2015-16 | 11738 ( 18.5) | 38130 (20.7) | 331 (18.5) | 4768 (19.8) | |
| dischargelocation (mean (sd)) | 5.15 (1.63) | 5.02 (1.64) | 7.17 (2.38) | 7.69 (2.18) | |
| dialysis (%) | 0 | 61202 ( 96.5) | 178604 (96.8) | 1691 (94.4) | 22997 (95.5) |
| 1 | 2225 ( 3.5) | 5856 ( 3.2) | 101 ( 5.6) | 1076 ( 4.5) | |
| aids (%) | 0 | 63396 (100.0) | 184261 (99.9) | 1790 (99.9) | 24042 (99.9) |
| 1 | 31 ( 0.0) | 199 ( 0.1) | 2 ( 0.1) | 31 ( 0.1) | |
| hepaticfailure (%) | FALSE | 62336 ( 98.3) | 180827 (98.0) | 1719 (95.9) | 23189 (96.3) |
| TRUE | 1091 ( 1.7) | 3633 ( 2.0) | 73 ( 4.1) | 884 ( 3.7) | |
| diabetes (%) | 0 | 49225 ( 77.6) | 143639 (77.9) | 1403 (78.3) | 19653 (81.6) |
| 1 | 14202 ( 22.4) | 40821 (22.1) | 389 (21.7) | 4420 (18.4) | |
| immunosuppression (%) | 0 | 62554 ( 98.6) | 180037 (97.6) | 1752 (97.8) | 23043 (95.7) |
| 1 | 873 ( 1.4) | 4423 ( 2.4) | 40 ( 2.2) | 1030 ( 4.3) | |
| leukemia (%) | 0 | 63177 ( 99.6) | 183156 (99.3) | 1787 (99.7) | 23694 (98.4) |
| 1 | 250 ( 0.4) | 1304 ( 0.7) | 5 ( 0.3) | 379 ( 1.6) | |
| lymphoma (%) | 0 | 63262 ( 99.7) | 183762 (99.6) | 1783 (99.5) | 23915 (99.3) |
| 1 | 165 ( 0.3) | 698 ( 0.4) | 9 ( 0.5) | 158 ( 0.7) | |
| metastaticcancer (%) | 0 | 62573 ( 98.7) | 180962 (98.1) | 1748 (97.5) | 23163 (96.2) |
| 1 | 854 ( 1.3) | 3498 ( 1.9) | 44 ( 2.5) | 910 ( 3.8) | |
| thrombolytics (%) | 0 | 61472 ( 96.9) | 181851 (98.6) | 1764 (98.4) | 23697 (98.4) |
| 1 | 1955 ( 3.1) | 2609 ( 1.4) | 28 ( 1.6) | 376 ( 1.6) | |
| sofa_respiration_baseline2 (%) | FALSE | 51153 ( 80.6) | 138294 (75.0) | 1296 (72.3) | 17265 (71.7) |
| TRUE | 12274 ( 19.4) | 46166 (25.0) | 496 (27.7) | 6808 (28.3) | |
| sofa_liver_baseline2 (%) | FALSE | 62336 ( 98.3) | 180827 (98.0) | 1719 (95.9) | 23189 (96.3) |
| TRUE | 1091 ( 1.7) | 3633 ( 2.0) | 73 ( 4.1) | 884 ( 3.7) | |
| sofa_renal_baseline2 (%) | FALSE | 61202 ( 96.5) | 178604 (96.8) | 1691 (94.4) | 22997 (95.5) |
| TRUE | 2225 ( 3.5) | 5856 ( 3.2) | 101 ( 5.6) | 1076 ( 4.5) | |
| cardiovascular_baseline (%) | 0 | 47719 ( 75.2) | 145389 (78.8) | 1135 (63.3) | 17618 (73.2) |
| 1 | 15708 ( 24.8) | 39071 (21.2) | 657 (36.7) | 6455 (26.8) | |
| group (%) | Cardiovascular | 27116 ( 42.8) | 53849 (29.2) | 534 (29.8) | 6864 (28.5) |
| Gastrointestinal | 5746 ( 9.1) | 20519 (11.1) | 160 ( 8.9) | 2119 ( 8.8) | |
| Gynaecological | 105 ( 0.2) | 601 ( 0.3) | 0 ( 0.0) | 9 ( 0.0) | |
| Hematological | 418 ( 0.7) | 1497 ( 0.8) | 11 ( 0.6) | 160 ( 0.7) | |
| Metabolic | 5782 ( 9.1) | 16247 ( 8.8) | 41 ( 2.3) | 391 ( 1.6) | |
| Muscoskeletal/Skin disease | 718 ( 1.1) | 2614 ( 1.4) | 8 ( 0.4) | 118 ( 0.5) | |
| Neurological | 10296 ( 16.2) | 23204 (12.6) | 364 (20.3) | 2973 (12.3) | |
| Renal/Genitourinary | 1532 ( 2.4) | 4569 ( 2.5) | 39 ( 2.2) | 436 ( 1.8) | |
| Respiratory | 5980 ( 9.4) | 29736 (16.1) | 364 (20.3) | 4778 (19.8) | |
| Sepsis | 2424 ( 3.8) | 21609 (11.7) | 185 (10.3) | 5119 (21.3) | |
| Trauma | 2837 ( 4.5) | 8359 ( 4.5) | 74 ( 4.1) | 855 ( 3.6) | |
| Undefined | 473 ( 0.7) | 1656 ( 0.9) | 12 ( 0.7) | 251 ( 1.0) |
vars5 <- c("age_Ranges", "gender2", "ethnicity2", "BMI_Ranges", "physicianSpeciality2", "icu_admit_source2", "icu_disch_location2", "hospitaldischargeyear", "dischargelocation", "dialysis", "aids", "hepaticfailure", "diabetes", "immunosuppression" , "leukemia", "lymphoma", "metastaticcancer", "thrombolytics", "sofa_respiration_baseline2", "sofa_liver_baseline2", "sofa_renal_baseline2", "cardiovascular_baseline", "group")
if(!("tableone" %in% rownames(installed.packages()))) {
install.packages("tableone")
}
library(dplyr); library(Hmisc); library(ggplot2); #library(sjPlot)
library(tableone)
CreateTableOne(data=ssd_incl_te ,vars=vars5,strata="qSOFA2TruthMort",test=FALSE, includeNA=TRUE
) %>% print(nonnormal= c("sofa_respiration_baseline2", "sofa_liver_baseline2", "sofa_renal_baseline2"),minMax=TRUE,
printToggle = FALSE,
showAllLevels = TRUE,
cramVars = "kon"
) %>%
{data.frame(
variable_name = gsub(" ", " ", rownames(.), fixed = TRUE), .,
row.names = NULL,
check.names = FALSE,
stringsAsFactors = FALSE)} %>%
knitr::kable(caption="qSOFA Positive Hospital Mortality TRUE/FALSE")| variable_name | level | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE |
|---|---|---|---|---|---|
| n | 87257 | 160630 | 2429 | 23436 | |
| age_Ranges (%) | (0,25] | 3389 ( 3.9) | 5412 ( 3.4) | 14 ( 0.6) | 236 ( 1.0) |
| (25,35] | 5308 ( 6.1) | 8224 ( 5.1) | 38 ( 1.6) | 490 ( 2.1) | |
| (35,45] | 7662 ( 8.8) | 11667 ( 7.3) | 92 ( 3.8) | 907 ( 3.9) | |
| (45,55] | 14184 (16.3) | 23743 (14.8) | 208 ( 8.6) | 2394 (10.2) | |
| (55,65] | 18886 (21.6) | 33397 (20.8) | 451 (18.6) | 4370 (18.6) | |
| (65,75] | 18746 (21.5) | 35645 (22.2) | 642 (26.4) | 5573 (23.8) | |
| (75,85] | 13930 (16.0) | 29059 (18.1) | 689 (28.4) | 5944 (25.4) | |
| (85,100] | 5152 ( 5.9) | 13483 ( 8.4) | 295 (12.1) | 3522 (15.0) | |
| gender2 (%) | Male | 49579 (56.8) | 83709 (52.1) | 1318 (54.3) | 12296 (52.5) |
| Female | 37660 (43.2) | 76898 (47.9) | 1106 (45.5) | 11106 (47.4) | |
| Other/Unknown | 18 ( 0.0) | 23 ( 0.0) | 5 ( 0.2) | 34 ( 0.1) | |
| ethnicity2 (%) | Caucasian | 64139 (73.5) | 124650 (77.6) | 1885 (77.6) | 18014 (76.9) |
| African American | 11434 (13.1) | 17516 (10.9) | 252 (10.4) | 2527 (10.8) | |
| Hispanic | 4310 ( 4.9) | 6787 ( 4.2) | 117 ( 4.8) | 1071 ( 4.6) | |
| Asian | 1074 ( 1.2) | 2097 ( 1.3) | 23 ( 0.9) | 339 ( 1.4) | |
| Native American | 620 ( 0.7) | 1214 ( 0.8) | 15 ( 0.6) | 163 ( 0.7) | |
| Other/Unknown | 5680 ( 6.5) | 8366 ( 5.2) | 137 ( 5.6) | 1322 ( 5.6) | |
| BMI_Ranges (%) | (0,18.5] | 3337 ( 3.8) | 8199 ( 5.1) | 166 ( 6.8) | 1746 ( 7.5) |
| (18.5,25] | 22470 (25.8) | 46106 (28.7) | 779 (32.1) | 7520 (32.1) | |
| (25,35] | 42118 (48.3) | 72645 (45.2) | 981 (40.4) | 9468 (40.4) | |
| (35,200] | 15898 (18.2) | 28601 (17.8) | 377 (15.5) | 3581 (15.3) | |
| Other/Unknown | 3434 ( 3.9) | 5079 ( 3.2) | 126 ( 5.2) | 1121 ( 4.8) | |
| physicianSpeciality2 (%) | Critical Care | 18845 (21.6) | 51695 (32.2) | 778 (32.0) | 8977 (38.3) |
| Speciality-Other | 68412 (78.4) | 108935 (67.8) | 1651 (68.0) | 14459 (61.7) | |
| icu_admit_source2 (%) | Floor | 12015 (13.8) | 27298 (17.0) | 632 (26.0) | 6489 (27.7) |
| OR/Proc Area | 18237 (20.9) | 32725 (20.4) | 242 (10.0) | 1727 ( 7.4) | |
| Direct Admit | 9788 (11.2) | 16628 (10.4) | 300 (12.4) | 2755 (11.8) | |
| Emergency Department | 45347 (52.0) | 79057 (49.2) | 1133 (46.6) | 11137 (47.5) | |
| Other | 580 ( 0.7) | 1415 ( 0.9) | 29 ( 1.2) | 336 ( 1.4) | |
| Step-Down Unit | 1290 ( 1.5) | 3507 ( 2.2) | 93 ( 3.8) | 992 ( 4.2) | |
| icu_disch_location2 (%) | Floor | 65372 (74.9) | 126936 (79.0) | 816 (33.6) | 6295 (26.9) |
| Death | 0 ( 0.0) | 0 ( 0.0) | 1552 (63.9) | 16803 (71.7) | |
| Home | 13771 (15.8) | 12890 ( 8.0) | 4 ( 0.2) | 18 ( 0.1) | |
| SNF/Rehab | 952 ( 1.1) | 3304 ( 2.1) | 0 ( 0.0) | 2 ( 0.0) | |
| Other | 2252 ( 2.6) | 6434 ( 4.0) | 19 ( 0.8) | 100 ( 0.4) | |
| Other Hospital | 1733 ( 2.0) | 4405 ( 2.7) | 2 ( 0.1) | 16 ( 0.1) | |
| Step-Down Unit | 3177 ( 3.6) | 6661 ( 4.1) | 36 ( 1.5) | 202 ( 0.9) | |
| hospitaldischargeyear (%) | -2010 | 12131 (13.9) | 17851 (11.1) | 455 (18.7) | 2911 (12.4) |
| 2011 | 12029 (13.8) | 21105 (13.1) | 393 (16.2) | 3287 (14.0) | |
| 2012 | 13867 (15.9) | 26684 (16.6) | 364 (15.0) | 3895 (16.6) | |
| 2013 | 15366 (17.6) | 30143 (18.8) | 412 (17.0) | 4341 (18.5) | |
| 2014 | 17035 (19.5) | 31808 (19.8) | 393 (16.2) | 4315 (18.4) | |
| 2015-16 | 16829 (19.3) | 33039 (20.6) | 412 (17.0) | 4687 (20.0) | |
| dischargelocation (mean (sd)) | 5.06 (1.60) | 5.05 (1.66) | 7.33 (2.34) | 7.68 (2.18) | |
| dialysis (%) | 0 | 84312 (96.6) | 155494 (96.8) | 2327 (95.8) | 22361 (95.4) |
| 1 | 2945 ( 3.4) | 5136 ( 3.2) | 102 ( 4.2) | 1075 ( 4.6) | |
| aids (%) | 0 | 87187 (99.9) | 160470 (99.9) | 2427 (99.9) | 23405 (99.9) |
| 1 | 70 ( 0.1) | 160 ( 0.1) | 2 ( 0.1) | 31 ( 0.1) | |
| hepaticfailure (%) | FALSE | 85884 (98.4) | 157279 (97.9) | 2365 (97.4) | 22543 (96.2) |
| TRUE | 1373 ( 1.6) | 3351 ( 2.1) | 64 ( 2.6) | 893 ( 3.8) | |
| diabetes (%) | 0 | 67023 (76.8) | 125841 (78.3) | 1952 (80.4) | 19104 (81.5) |
| 1 | 20234 (23.2) | 34789 (21.7) | 477 (19.6) | 4332 (18.5) | |
| immunosuppression (%) | 0 | 85620 (98.1) | 156971 (97.7) | 2308 (95.0) | 22487 (96.0) |
| 1 | 1637 ( 1.9) | 3659 ( 2.3) | 121 ( 5.0) | 949 ( 4.0) | |
| leukemia (%) | 0 | 86780 (99.5) | 159553 (99.3) | 2397 (98.7) | 23084 (98.5) |
| 1 | 477 ( 0.5) | 1077 ( 0.7) | 32 ( 1.3) | 352 ( 1.5) | |
| lymphoma (%) | 0 | 87015 (99.7) | 160009 (99.6) | 2413 (99.3) | 23285 (99.4) |
| 1 | 242 ( 0.3) | 621 ( 0.4) | 16 ( 0.7) | 151 ( 0.6) | |
| metastaticcancer (%) | 0 | 85825 (98.4) | 157710 (98.2) | 2335 (96.1) | 22576 (96.3) |
| 1 | 1432 ( 1.6) | 2920 ( 1.8) | 94 ( 3.9) | 860 ( 3.7) | |
| thrombolytics (%) | 0 | 85090 (97.5) | 158233 (98.5) | 2391 (98.4) | 23070 (98.4) |
| 1 | 2167 ( 2.5) | 2397 ( 1.5) | 38 ( 1.6) | 366 ( 1.6) | |
| sofa_respiration_baseline2 (%) | FALSE | 69286 (79.4) | 120161 (74.8) | 1672 (68.8) | 16889 (72.1) |
| TRUE | 17971 (20.6) | 40469 (25.2) | 757 (31.2) | 6547 (27.9) | |
| sofa_liver_baseline2 (%) | FALSE | 85884 (98.4) | 157279 (97.9) | 2365 (97.4) | 22543 (96.2) |
| TRUE | 1373 ( 1.6) | 3351 ( 2.1) | 64 ( 2.6) | 893 ( 3.8) | |
| sofa_renal_baseline2 (%) | FALSE | 84312 (96.6) | 155494 (96.8) | 2327 (95.8) | 22361 (95.4) |
| TRUE | 2945 ( 3.4) | 5136 ( 3.2) | 102 ( 4.2) | 1075 ( 4.6) | |
| cardiovascular_baseline (%) | 0 | 69275 (79.4) | 123833 (77.1) | 1744 (71.8) | 17009 (72.6) |
| 1 | 17982 (20.6) | 36797 (22.9) | 685 (28.2) | 6427 (27.4) | |
| group (%) | Cardiovascular | 33024 (37.8) | 47941 (29.8) | 690 (28.4) | 6708 (28.6) |
| Gastrointestinal | 9742 (11.2) | 16523 (10.3) | 211 ( 8.7) | 2068 ( 8.8) | |
| Gynaecological | 276 ( 0.3) | 430 ( 0.3) | 0 ( 0.0) | 9 ( 0.0) | |
| Hematological | 795 ( 0.9) | 1120 ( 0.7) | 18 ( 0.7) | 153 ( 0.7) | |
| Metabolic | 8223 ( 9.4) | 13806 ( 8.6) | 38 ( 1.6) | 394 ( 1.7) | |
| Muscoskeletal/Skin disease | 1196 ( 1.4) | 2136 ( 1.3) | 11 ( 0.5) | 115 ( 0.5) | |
| Neurological | 11591 (13.3) | 21909 (13.6) | 429 (17.7) | 2908 (12.4) | |
| Renal/Genitourinary | 2151 ( 2.5) | 3950 ( 2.5) | 45 ( 1.9) | 430 ( 1.8) | |
| Respiratory | 10416 (11.9) | 25300 (15.8) | 542 (22.3) | 4600 (19.6) | |
| Sepsis | 4434 ( 5.1) | 19599 (12.2) | 303 (12.5) | 5001 (21.3) | |
| Trauma | 4534 ( 5.2) | 6662 ( 4.1) | 108 ( 4.4) | 821 ( 3.5) | |
| Undefined | 875 ( 1.0) | 1254 ( 0.8) | 34 ( 1.4) | 229 ( 1.0) |
vars5 <- c("age_Ranges", "gender2", "ethnicity2", "BMI_Ranges", "physicianSpeciality2", "icu_admit_source2", "icu_disch_location2", "hospitaldischargeyear", "dischargelocation", "dialysis", "aids", "hepaticfailure", "diabetes", "immunosuppression" , "leukemia", "lymphoma", "metastaticcancer", "thrombolytics", "sofa_respiration_baseline2", "sofa_liver_baseline2", "sofa_renal_baseline2", "cardiovascular_baseline", "group")
if(!("tableone" %in% rownames(installed.packages()))) {
install.packages("tableone")
}
library(tableone)
CreateTableOne(data=ssd_incl_te ,vars=vars5,strata="SOFA2TruthMort",test=FALSE, includeNA=TRUE
) %>% print(nonnormal= c("sofa_respiration_baseline2", "sofa_liver_baseline2", "sofa_renal_baseline2"),minMax=TRUE,
printToggle = FALSE,
showAllLevels = TRUE,
cramVars = "kon"
) %>%
{data.frame(
variable_name = gsub(" ", " ", rownames(.), fixed = TRUE), .,
row.names = NULL,
check.names = FALSE,
stringsAsFactors = FALSE)} %>%
knitr::kable(caption="SOFA Positive Hospital Mortality TRUE/FALSE")| variable_name | level | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE |
|---|---|---|---|---|---|
| n | 83807 | 164080 | 1464 | 24401 | |
| age_Ranges (%) | (0,25] | 4029 ( 4.8) | 4772 ( 2.9) | 5 ( 0.3) | 245 ( 1.0) |
| (25,35] | 5833 ( 7.0) | 7699 ( 4.7) | 14 ( 1.0) | 514 ( 2.1) | |
| (35,45] | 8346 (10.0) | 10983 ( 6.7) | 35 ( 2.4) | 964 ( 4.0) | |
| (45,55] | 15061 (18.0) | 22866 (13.9) | 120 ( 8.2) | 2482 (10.2) | |
| (55,65] | 18448 (22.0) | 33835 (20.6) | 296 (20.2) | 4525 (18.5) | |
| (65,75] | 16686 (19.9) | 37705 (23.0) | 402 (27.5) | 5813 (23.8) | |
| (75,85] | 11248 (13.4) | 31741 (19.3) | 405 (27.7) | 6228 (25.5) | |
| (85,100] | 4156 ( 5.0) | 14479 ( 8.8) | 187 (12.8) | 3630 (14.9) | |
| gender2 (%) | Male | 43050 (51.4) | 90238 (55.0) | 692 (47.3) | 12922 (53.0) |
| Female | 40746 (48.6) | 73812 (45.0) | 770 (52.6) | 11442 (46.9) | |
| Other/Unknown | 11 ( 0.0) | 30 ( 0.0) | 2 ( 0.1) | 37 ( 0.2) | |
| ethnicity2 (%) | Caucasian | 63802 (76.1) | 124987 (76.2) | 1207 (82.4) | 18692 (76.6) |
| African American | 9866 (11.8) | 19084 (11.6) | 111 ( 7.6) | 2668 (10.9) | |
| Hispanic | 3658 ( 4.4) | 7439 ( 4.5) | 52 ( 3.6) | 1136 ( 4.7) | |
| Asian | 1019 ( 1.2) | 2152 ( 1.3) | 20 ( 1.4) | 342 ( 1.4) | |
| Native American | 553 ( 0.7) | 1281 ( 0.8) | 1 ( 0.1) | 177 ( 0.7) | |
| Other/Unknown | 4909 ( 5.9) | 9137 ( 5.6) | 73 ( 5.0) | 1386 ( 5.7) | |
| BMI_Ranges (%) | (0,18.5] | 3586 ( 4.3) | 7950 ( 4.8) | 155 (10.6) | 1757 ( 7.2) |
| (18.5,25] | 22640 (27.0) | 45936 (28.0) | 519 (35.5) | 7780 (31.9) | |
| (25,35] | 39257 (46.8) | 75506 (46.0) | 569 (38.9) | 9880 (40.5) | |
| (35,200] | 14808 (17.7) | 29691 (18.1) | 166 (11.3) | 3792 (15.5) | |
| Other/Unknown | 3516 ( 4.2) | 4997 ( 3.0) | 55 ( 3.8) | 1192 ( 4.9) | |
| physicianSpeciality2 (%) | Critical Care | 16917 (20.2) | 53623 (32.7) | 471 (32.2) | 9284 (38.0) |
| Speciality-Other | 66890 (79.8) | 110457 (67.3) | 993 (67.8) | 15117 (62.0) | |
| icu_admit_source2 (%) | Floor | 11167 (13.3) | 28146 (17.2) | 488 (33.3) | 6633 (27.2) |
| OR/Proc Area | 15787 (18.8) | 35175 (21.4) | 87 ( 5.9) | 1882 ( 7.7) | |
| Direct Admit | 9574 (11.4) | 16842 (10.3) | 154 (10.5) | 2901 (11.9) | |
| Emergency Department | 45511 (54.3) | 78893 (48.1) | 654 (44.7) | 11616 (47.6) | |
| Other | 551 ( 0.7) | 1444 ( 0.9) | 19 ( 1.3) | 346 ( 1.4) | |
| Step-Down Unit | 1217 ( 1.5) | 3580 ( 2.2) | 62 ( 4.2) | 1023 ( 4.2) | |
| icu_disch_location2 (%) | Floor | 62101 (74.1) | 130207 (79.4) | 593 (40.5) | 6518 (26.7) |
| Death | 0 ( 0.0) | 0 ( 0.0) | 830 (56.7) | 17525 (71.8) | |
| Home | 14699 (17.5) | 11962 ( 7.3) | 2 ( 0.1) | 20 ( 0.1) | |
| SNF/Rehab | 683 ( 0.8) | 3573 ( 2.2) | 0 ( 0.0) | 2 ( 0.0) | |
| Other | 2198 ( 2.6) | 6488 ( 4.0) | 5 ( 0.3) | 114 ( 0.5) | |
| Other Hospital | 1623 ( 1.9) | 4515 ( 2.8) | 6 ( 0.4) | 12 ( 0.0) | |
| Step-Down Unit | 2503 ( 3.0) | 7335 ( 4.5) | 28 ( 1.9) | 210 ( 0.9) | |
| hospitaldischargeyear (%) | -2010 | 9788 (11.7) | 20194 (12.3) | 193 (13.2) | 3173 (13.0) |
| 2011 | 10699 (12.8) | 22435 (13.7) | 200 (13.7) | 3480 (14.3) | |
| 2012 | 13477 (16.1) | 27074 (16.5) | 234 (16.0) | 4025 (16.5) | |
| 2013 | 15974 (19.1) | 29535 (18.0) | 287 (19.6) | 4466 (18.3) | |
| 2014 | 17191 (20.5) | 31652 (19.3) | 263 (18.0) | 4445 (18.2) | |
| 2015-16 | 16678 (19.9) | 33190 (20.2) | 287 (19.6) | 4812 (19.7) | |
| dischargelocation (mean (sd)) | 5.16 (1.65) | 5.00 (1.63) | 7.01 (2.41) | 7.69 (2.18) | |
| dialysis (%) | 0 | 80629 (96.2) | 159177 (97.0) | 1390 (94.9) | 23298 (95.5) |
| 1 | 3178 ( 3.8) | 4903 ( 3.0) | 74 ( 5.1) | 1103 ( 4.5) | |
| aids (%) | 0 | 83751 (99.9) | 163906 (99.9) | 1462 (99.9) | 24370 (99.9) |
| 1 | 56 ( 0.1) | 174 ( 0.1) | 2 ( 0.1) | 31 ( 0.1) | |
| hepaticfailure (%) | FALSE | 83104 (99.2) | 160059 (97.5) | 1438 (98.2) | 23470 (96.2) |
| TRUE | 703 ( 0.8) | 4021 ( 2.5) | 26 ( 1.8) | 931 ( 3.8) | |
| diabetes (%) | 0 | 66157 (78.9) | 126707 (77.2) | 1217 (83.1) | 19839 (81.3) |
| 1 | 17650 (21.1) | 37373 (22.8) | 247 (16.9) | 4562 (18.7) | |
| immunosuppression (%) | 0 | 82356 (98.3) | 160235 (97.7) | 1372 (93.7) | 23423 (96.0) |
| 1 | 1451 ( 1.7) | 3845 ( 2.3) | 92 ( 6.3) | 978 ( 4.0) | |
| leukemia (%) | 0 | 83514 (99.7) | 162819 (99.2) | 1454 (99.3) | 24027 (98.5) |
| 1 | 293 ( 0.3) | 1261 ( 0.8) | 10 ( 0.7) | 374 ( 1.5) | |
| lymphoma (%) | 0 | 83612 (99.8) | 163412 (99.6) | 1459 (99.7) | 24239 (99.3) |
| 1 | 195 ( 0.2) | 668 ( 0.4) | 5 ( 0.3) | 162 ( 0.7) | |
| metastaticcancer (%) | 0 | 82448 (98.4) | 161087 (98.2) | 1372 (93.7) | 23539 (96.5) |
| 1 | 1359 ( 1.6) | 2993 ( 1.8) | 92 ( 6.3) | 862 ( 3.5) | |
| thrombolytics (%) | 0 | 81143 (96.8) | 162180 (98.8) | 1439 (98.3) | 24022 (98.4) |
| 1 | 2664 ( 3.2) | 1900 ( 1.2) | 25 ( 1.7) | 379 ( 1.6) | |
| sofa_respiration_baseline2 (%) | FALSE | 64372 (76.8) | 125075 (76.2) | 788 (53.8) | 17773 (72.8) |
| TRUE | 19435 (23.2) | 39005 (23.8) | 676 (46.2) | 6628 (27.2) | |
| sofa_liver_baseline2 (%) | FALSE | 83104 (99.2) | 160059 (97.5) | 1438 (98.2) | 23470 (96.2) |
| TRUE | 703 ( 0.8) | 4021 ( 2.5) | 26 ( 1.8) | 931 ( 3.8) | |
| sofa_renal_baseline2 (%) | FALSE | 80629 (96.2) | 159177 (97.0) | 1390 (94.9) | 23298 (95.5) |
| TRUE | 3178 ( 3.8) | 4903 ( 3.0) | 74 ( 5.1) | 1103 ( 4.5) | |
| cardiovascular_baseline (%) | 0 | 68828 (82.1) | 124280 (75.7) | 1060 (72.4) | 17693 (72.5) |
| 1 | 14979 (17.9) | 39800 (24.3) | 404 (27.6) | 6708 (27.5) | |
| group (%) | Cardiovascular | 30780 (36.7) | 50185 (30.6) | 343 (23.4) | 7055 (28.9) |
| Gastrointestinal | 8099 ( 9.7) | 18166 (11.1) | 109 ( 7.4) | 2170 ( 8.9) | |
| Gynaecological | 263 ( 0.3) | 443 ( 0.3) | 3 ( 0.2) | 6 ( 0.0) | |
| Hematological | 483 ( 0.6) | 1432 ( 0.9) | 5 ( 0.3) | 166 ( 0.7) | |
| Metabolic | 8569 (10.2) | 13460 ( 8.2) | 15 ( 1.0) | 417 ( 1.7) | |
| Muscoskeletal/Skin disease | 1209 ( 1.4) | 2123 ( 1.3) | 4 ( 0.3) | 122 ( 0.5) | |
| Neurological | 12651 (15.1) | 20849 (12.7) | 159 (10.9) | 3178 (13.0) | |
| Renal/Genitourinary | 980 ( 1.2) | 5121 ( 3.1) | 15 ( 1.0) | 460 ( 1.9) | |
| Respiratory | 12189 (14.5) | 23527 (14.3) | 576 (39.3) | 4566 (18.7) | |
| Sepsis | 3416 ( 4.1) | 20617 (12.6) | 154 (10.5) | 5150 (21.1) | |
| Trauma | 4140 ( 4.9) | 7056 ( 4.3) | 36 ( 2.5) | 893 ( 3.7) | |
| Undefined | 1028 ( 1.2) | 1101 ( 0.7) | 45 ( 3.1) | 218 ( 0.9) |
vars5 <- c("age_Ranges", "gender2", "ethnicity2", "BMI_Ranges", "physicianSpeciality2", "icu_admit_source2", "icu_disch_location2", "hospitaldischargeyear", "dischargelocation", "dialysis", "aids", "hepaticfailure", "diabetes", "immunosuppression" , "leukemia", "lymphoma", "metastaticcancer", "thrombolytics", "sofa_respiration_baseline2", "sofa_liver_baseline2", "sofa_renal_baseline2", "cardiovascular_baseline", "group")
library(dplyr); library(Hmisc); library(ggplot2); #library(sjPlot)
if(!("tableone" %in% rownames(installed.packages()))) {
install.packages("tableone")
}
library(dplyr); library(Hmisc); library(ggplot2); #library(sjPlot)
library(tableone)
CreateTableOne(data=ssd_incl_te ,vars=vars5,strata="FuzzyLogicTruthMort",test=FALSE, includeNA=TRUE
) %>% print(nonnormal= c("sofa_respiration_baseline2", "sofa_liver_baseline2", "sofa_renal_baseline2"),minMax=TRUE,
printToggle = FALSE,
showAllLevels = TRUE,
cramVars = "kon"
) %>%
{data.frame(
variable_name = gsub(" ", " ", rownames(.), fixed = TRUE), .,
row.names = NULL,
check.names = FALSE,
stringsAsFactors = FALSE)} %>%
knitr::kable(caption="FuzzyLogic Positive Hospital Mortality TRUE/FALSE")| variable_name | level | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE |
|---|---|---|---|---|---|
| n | 119438 | 128449 | 3492 | 22373 | |
| age_Ranges (%) | (0,25] | 4013 ( 3.4) | 4788 ( 3.7) | 10 ( 0.3) | 240 ( 1.1) |
| (25,35] | 6627 ( 5.5) | 6905 ( 5.4) | 38 ( 1.1) | 490 ( 2.2) | |
| (35,45] | 9846 ( 8.2) | 9483 ( 7.4) | 93 ( 2.7) | 906 ( 4.0) | |
| (45,55] | 18948 (15.9) | 18979 (14.8) | 266 ( 7.6) | 2336 (10.4) | |
| (55,65] | 25293 (21.2) | 26990 (21.0) | 560 (16.0) | 4261 (19.0) | |
| (65,75] | 25677 (21.5) | 28714 (22.4) | 836 (23.9) | 5379 (24.0) | |
| (75,85] | 20248 (17.0) | 22741 (17.7) | 1042 (29.8) | 5591 (25.0) | |
| (85,100] | 8786 ( 7.4) | 9849 ( 7.7) | 647 (18.5) | 3170 (14.2) | |
| gender2 (%) | Male | 65930 (55.2) | 67358 (52.4) | 1846 (52.9) | 11768 (52.6) |
| Female | 53490 (44.8) | 61068 (47.5) | 1638 (46.9) | 10574 (47.3) | |
| Other/Unknown | 18 ( 0.0) | 23 ( 0.0) | 8 ( 0.2) | 31 ( 0.1) | |
| ethnicity2 (%) | Caucasian | 89699 (75.1) | 99090 (77.1) | 2680 (76.7) | 17219 (77.0) |
| African American | 15185 (12.7) | 13765 (10.7) | 393 (11.3) | 2386 (10.7) | |
| Hispanic | 5262 ( 4.4) | 5835 ( 4.5) | 137 ( 3.9) | 1051 ( 4.7) | |
| Asian | 1590 ( 1.3) | 1581 ( 1.2) | 53 ( 1.5) | 309 ( 1.4) | |
| Native American | 865 ( 0.7) | 969 ( 0.8) | 19 ( 0.5) | 159 ( 0.7) | |
| Other/Unknown | 6837 ( 5.7) | 7209 ( 5.6) | 210 ( 6.0) | 1249 ( 5.6) | |
| BMI_Ranges (%) | (0,18.5] | 4891 ( 4.1) | 6645 ( 5.2) | 244 ( 7.0) | 1668 ( 7.5) |
| (18.5,25] | 32335 (27.1) | 36241 (28.2) | 1131 (32.4) | 7168 (32.0) | |
| (25,35] | 56696 (47.5) | 58067 (45.2) | 1420 (40.7) | 9029 (40.4) | |
| (35,200] | 20582 (17.2) | 23917 (18.6) | 506 (14.5) | 3452 (15.4) | |
| Other/Unknown | 4934 ( 4.1) | 3579 ( 2.8) | 191 ( 5.5) | 1056 ( 4.7) | |
| physicianSpeciality2 (%) | Critical Care | 26125 (21.9) | 44415 (34.6) | 1099 (31.5) | 8656 (38.7) |
| Speciality-Other | 93313 (78.1) | 84034 (65.4) | 2393 (68.5) | 13717 (61.3) | |
| icu_admit_source2 (%) | Floor | 17596 (14.7) | 21717 (16.9) | 962 (27.5) | 6159 (27.5) |
| OR/Proc Area | 22718 (19.0) | 28244 (22.0) | 261 ( 7.5) | 1708 ( 7.6) | |
| Direct Admit | 15459 (12.9) | 10957 ( 8.5) | 518 (14.8) | 2537 (11.3) | |
| Emergency Department | 60592 (50.7) | 63812 (49.7) | 1542 (44.2) | 10728 (48.0) | |
| Other | 955 ( 0.8) | 1040 ( 0.8) | 63 ( 1.8) | 302 ( 1.3) | |
| Step-Down Unit | 2118 ( 1.8) | 2679 ( 2.1) | 146 ( 4.2) | 939 ( 4.2) | |
| icu_disch_location2 (%) | Floor | 88826 (74.4) | 103482 (80.6) | 1415 (40.5) | 5696 (25.5) |
| Death | 0 ( 0.0) | 0 ( 0.0) | 1983 (56.8) | 16372 (73.2) | |
| Home | 19229 (16.1) | 7432 ( 5.8) | 3 ( 0.1) | 19 ( 0.1) | |
| SNF/Rehab | 1476 ( 1.2) | 2780 ( 2.2) | 0 ( 0.0) | 2 ( 0.0) | |
| Other | 3571 ( 3.0) | 5115 ( 4.0) | 23 ( 0.7) | 96 ( 0.4) | |
| Other Hospital | 2457 ( 2.1) | 3681 ( 2.9) | 9 ( 0.3) | 9 ( 0.0) | |
| Step-Down Unit | 3879 ( 3.2) | 5959 ( 4.6) | 59 ( 1.7) | 179 ( 0.8) | |
| hospitaldischargeyear (%) | -2010 | 14311 (12.0) | 15671 (12.2) | 480 (13.7) | 2886 (12.9) |
| 2011 | 15532 (13.0) | 17602 (13.7) | 467 (13.4) | 3213 (14.4) | |
| 2012 | 19360 (16.2) | 21191 (16.5) | 571 (16.4) | 3688 (16.5) | |
| 2013 | 22159 (18.6) | 23350 (18.2) | 683 (19.6) | 4070 (18.2) | |
| 2014 | 24018 (20.1) | 24825 (19.3) | 630 (18.0) | 4078 (18.2) | |
| 2015-16 | 24058 (20.1) | 25810 (20.1) | 661 (18.9) | 4438 (19.8) | |
| dischargelocation (mean (sd)) | 5.15 (1.65) | 4.97 (1.62) | 7.00 (2.42) | 7.75 (2.15) | |
| dialysis (%) | 0 | 115245 (96.5) | 124561 (97.0) | 3281 (94.0) | 21407 (95.7) |
| 1 | 4193 ( 3.5) | 3888 ( 3.0) | 211 ( 6.0) | 966 ( 4.3) | |
| aids (%) | 0 | 119343 (99.9) | 128314 (99.9) | 3486 (99.8) | 22346 (99.9) |
| 1 | 95 ( 0.1) | 135 ( 0.1) | 6 ( 0.2) | 27 ( 0.1) | |
| hepaticfailure (%) | FALSE | 117974 (98.8) | 125189 (97.5) | 3435 (98.4) | 21473 (96.0) |
| TRUE | 1464 ( 1.2) | 3260 ( 2.5) | 57 ( 1.6) | 900 ( 4.0) | |
| diabetes (%) | 0 | 89700 (75.1) | 103164 (80.3) | 2498 (71.5) | 18558 (82.9) |
| 1 | 29738 (24.9) | 25285 (19.7) | 994 (28.5) | 3815 (17.1) | |
| immunosuppression (%) | 0 | 117440 (98.3) | 125151 (97.4) | 3364 (96.3) | 21431 (95.8) |
| 1 | 1998 ( 1.7) | 3298 ( 2.6) | 128 ( 3.7) | 942 ( 4.2) | |
| leukemia (%) | 0 | 118868 (99.5) | 127465 (99.2) | 3450 (98.8) | 22031 (98.5) |
| 1 | 570 ( 0.5) | 984 ( 0.8) | 42 ( 1.2) | 342 ( 1.5) | |
| lymphoma (%) | 0 | 119099 (99.7) | 127925 (99.6) | 3468 (99.3) | 22230 (99.4) |
| 1 | 339 ( 0.3) | 524 ( 0.4) | 24 ( 0.7) | 143 ( 0.6) | |
| metastaticcancer (%) | 0 | 117589 (98.5) | 125946 (98.1) | 3389 (97.1) | 21522 (96.2) |
| 1 | 1849 ( 1.5) | 2503 ( 1.9) | 103 ( 2.9) | 851 ( 3.8) | |
| thrombolytics (%) | 0 | 116194 (97.3) | 127129 (99.0) | 3444 (98.6) | 22017 (98.4) |
| 1 | 3244 ( 2.7) | 1320 ( 1.0) | 48 ( 1.4) | 356 ( 1.6) | |
| sofa_respiration_baseline2 (%) | FALSE | 95583 (80.0) | 93864 (73.1) | 2514 (72.0) | 16047 (71.7) |
| TRUE | 23855 (20.0) | 34585 (26.9) | 978 (28.0) | 6326 (28.3) | |
| sofa_liver_baseline2 (%) | FALSE | 117974 (98.8) | 125189 (97.5) | 3435 (98.4) | 21473 (96.0) |
| TRUE | 1464 ( 1.2) | 3260 ( 2.5) | 57 ( 1.6) | 900 ( 4.0) | |
| sofa_renal_baseline2 (%) | FALSE | 115245 (96.5) | 124561 (97.0) | 3281 (94.0) | 21407 (95.7) |
| TRUE | 4193 ( 3.5) | 3888 ( 3.0) | 211 ( 6.0) | 966 ( 4.3) | |
| cardiovascular_baseline (%) | 0 | 93442 (78.2) | 99666 (77.6) | 2390 (68.4) | 16363 (73.1) |
| 1 | 25996 (21.8) | 28783 (22.4) | 1102 (31.6) | 6010 (26.9) | |
| group (%) | Cardiovascular | 46150 (38.6) | 34815 (27.1) | 883 (25.3) | 6515 (29.1) |
| Gastrointestinal | 10652 ( 8.9) | 15613 (12.2) | 193 ( 5.5) | 2086 ( 9.3) | |
| Gynaecological | 247 ( 0.2) | 459 ( 0.4) | 1 ( 0.0) | 8 ( 0.0) | |
| Hematological | 852 ( 0.7) | 1063 ( 0.8) | 22 ( 0.6) | 149 ( 0.7) | |
| Metabolic | 11088 ( 9.3) | 10941 ( 8.5) | 58 ( 1.7) | 374 ( 1.7) | |
| Muscoskeletal/Skin disease | 1538 ( 1.3) | 1794 ( 1.4) | 16 ( 0.5) | 110 ( 0.5) | |
| Neurological | 21786 (18.2) | 11714 ( 9.1) | 1048 (30.0) | 2289 (10.2) | |
| Renal/Genitourinary | 2731 ( 2.3) | 3370 ( 2.6) | 60 ( 1.7) | 415 ( 1.9) | |
| Respiratory | 13352 (11.2) | 22364 (17.4) | 784 (22.5) | 4358 (19.5) | |
| Sepsis | 4077 ( 3.4) | 19956 (15.5) | 242 ( 6.9) | 5062 (22.6) | |
| Trauma | 5785 ( 4.8) | 5411 ( 4.2) | 140 ( 4.0) | 789 ( 3.5) | |
| Undefined | 1180 ( 1.0) | 949 ( 0.7) | 45 ( 1.3) | 218 ( 1.0) |
library(tidyr)
ssd_incl_te%>% group_by(gender2=="Male",FuzzyLogicTruthMort) %>%summarise(n=n())%>%spread(FuzzyLogicTruthMort,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| gender2 == “Male” | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| FALSE | 53508 | 61091 | 1646 | 10605 | 0.8656436 | 0.4669151 |
| TRUE | 65930 | 67358 | 1846 | 11768 | 0.8644043 | 0.4946432 |
ssd_incl_te%>% group_by(ethnicity2,FuzzyLogicTruthMort) %>%summarise(n=n())%>%spread(FuzzyLogicTruthMort,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| ethnicity2 | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| Caucasian | 89699 | 99090 | 2680 | 17219 | 0.8653199 | 0.4751283 |
| African American | 15185 | 13765 | 393 | 2386 | 0.8585822 | 0.5245250 |
| Hispanic | 5262 | 5835 | 137 | 1051 | 0.8846801 | 0.4741822 |
| Asian | 1590 | 1581 | 53 | 309 | 0.8535912 | 0.5014191 |
| Native American | 865 | 969 | 19 | 159 | 0.8932584 | 0.4716467 |
| Other/Unknown | 6837 | 7209 | 210 | 1249 | 0.8560658 | 0.4867578 |
ssd_incl_te%>% group_by(icu_admit_source2,FuzzyLogicTruthMort) %>%summarise(n=n())%>%spread(FuzzyLogicTruthMort,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| icu_admit_source2 | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| Floor | 17596 | 21717 | 962 | 6159 | 0.8649066 | 0.4475873 |
| OR/Proc Area | 22718 | 28244 | 261 | 1708 | 0.8674454 | 0.4457831 |
| Direct Admit | 15459 | 10957 | 518 | 2537 | 0.8304419 | 0.5852135 |
| Emergency Department | 60592 | 63812 | 1542 | 10728 | 0.8743276 | 0.4870583 |
| Other | 955 | 1040 | 63 | 302 | 0.8273973 | 0.4786967 |
| Step-Down Unit | 2118 | 2679 | 146 | 939 | 0.8654378 | 0.4415260 |
21 Baseline Sepsis Test/Train
Baseline_Sepsis_tr<-glm(sepsis_outcome ~ age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status + hospital_size + physicianSpeciality2 + hospitaldischargeyear + dialysis + aids + hepaticfailure + diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer + thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline, data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(Baseline_Sepsis_tr)
#sjt.glm(Baseline_Sepsis_tr)
#drop1(Baseline_Sepsis_tr,test="Chisq")
summary(Baseline_Sepsis_tr)##
## Call:
## glm(formula = sepsis_outcome ~ age_Ranges + gender2 + ethnicity2 +
## BMI_Ranges + icu_admit_source2 + hospital_teaching_status +
## hospital_size + physicianSpeciality2 + hospitaldischargeyear +
## dialysis + aids + hepaticfailure + diabetes + immunosuppression +
## leukemia + lymphoma + metastaticcancer + thrombolytics +
## sofa_respiration_baseline2 + cardiovascular_baseline, family = "binomial",
## data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.0071 -0.7316 -0.5589 -0.2665 3.3612
##
## Coefficients:
## Estimate Std. Error z value
## (Intercept) -0.948952 0.032059 -29.600
## age_Ranges(25,35] 0.157222 0.026835 5.859
## age_Ranges(35,45] 0.305391 0.024934 12.248
## age_Ranges(45,55] 0.480932 0.023066 20.851
## age_Ranges(55,65] 0.664639 0.022559 29.463
## age_Ranges(65,75] 0.718137 0.022549 31.849
## age_Ranges(75,85] 0.801259 0.022662 35.357
## age_Ranges(85,100] 0.934297 0.023815 39.232
## gender2Female 0.055373 0.006581 8.414
## gender2Other/Unknown -0.933627 0.263338 -3.545
## ethnicity2African American -0.095562 0.010658 -8.966
## ethnicity2Hispanic 0.395323 0.014683 26.923
## ethnicity2Asian 0.083708 0.028682 2.918
## ethnicity2Native American 0.322652 0.036496 8.841
## ethnicity2Other/Unknown 0.073306 0.014404 5.089
## BMI_Ranges(18.5,25] -0.259430 0.014657 -17.700
## BMI_Ranges(25,35] -0.346922 0.014359 -24.160
## BMI_Ranges(35,200] -0.142435 0.015579 -9.143
## BMI_RangesOther/Unknown -0.604858 0.022942 -26.364
## icu_admit_source2OR/Proc Area -1.957638 0.014310 -136.805
## icu_admit_source2Direct Admit -0.619162 0.012410 -49.891
## icu_admit_source2Emergency Department -0.320082 0.008116 -39.439
## icu_admit_source2Other -0.188787 0.032393 -5.828
## icu_admit_source2Step-Down Unit 0.033255 0.020519 1.621
## hospital_teaching_statusf -0.211799 0.023996 -8.827
## hospital_teaching_statust -0.161197 0.024168 -6.670
## hospital_size<100 0.537067 0.022878 23.476
## hospital_size100-249 0.273145 0.018688 14.616
## hospital_size250-500 0.262396 0.019027 13.791
## hospital_size>500 0.124338 0.017769 6.997
## physicianSpeciality2Speciality-Other -0.640748 0.007362 -87.036
## hospitaldischargeyear2011 0.100206 0.012669 7.910
## hospitaldischargeyear2012 -0.043243 0.012306 -3.514
## hospitaldischargeyear2013 -0.050617 0.012027 -4.208
## hospitaldischargeyear2014 -0.090001 0.011937 -7.540
## hospitaldischargeyear2015-16 -0.036695 0.011814 -3.106
## dialysis1 0.246276 0.017038 14.455
## aids1 1.344545 0.084849 15.846
## hepaticfailureTRUE 0.183669 0.020985 8.752
## diabetes1 -0.074419 0.008111 -9.175
## immunosuppression1 0.590598 0.019733 29.929
## leukemia1 0.508674 0.032829 15.494
## lymphoma1 0.411006 0.044722 9.190
## metastaticcancer1 0.096858 0.023419 4.136
## thrombolytics1 -2.219547 0.060013 -36.985
## sofa_respiration_baseline2TRUE 0.477844 0.007251 65.897
## cardiovascular_baseline1 -0.069130 0.007952 -8.694
## Pr(>|z|)
## (Intercept) < 2e-16 ***
## age_Ranges(25,35] 4.66e-09 ***
## age_Ranges(35,45] < 2e-16 ***
## age_Ranges(45,55] < 2e-16 ***
## age_Ranges(55,65] < 2e-16 ***
## age_Ranges(65,75] < 2e-16 ***
## age_Ranges(75,85] < 2e-16 ***
## age_Ranges(85,100] < 2e-16 ***
## gender2Female < 2e-16 ***
## gender2Other/Unknown 0.000392 ***
## ethnicity2African American < 2e-16 ***
## ethnicity2Hispanic < 2e-16 ***
## ethnicity2Asian 0.003518 **
## ethnicity2Native American < 2e-16 ***
## ethnicity2Other/Unknown 3.59e-07 ***
## BMI_Ranges(18.5,25] < 2e-16 ***
## BMI_Ranges(25,35] < 2e-16 ***
## BMI_Ranges(35,200] < 2e-16 ***
## BMI_RangesOther/Unknown < 2e-16 ***
## icu_admit_source2OR/Proc Area < 2e-16 ***
## icu_admit_source2Direct Admit < 2e-16 ***
## icu_admit_source2Emergency Department < 2e-16 ***
## icu_admit_source2Other 5.61e-09 ***
## icu_admit_source2Step-Down Unit 0.105083
## hospital_teaching_statusf < 2e-16 ***
## hospital_teaching_statust 2.56e-11 ***
## hospital_size<100 < 2e-16 ***
## hospital_size100-249 < 2e-16 ***
## hospital_size250-500 < 2e-16 ***
## hospital_size>500 2.61e-12 ***
## physicianSpeciality2Speciality-Other < 2e-16 ***
## hospitaldischargeyear2011 2.58e-15 ***
## hospitaldischargeyear2012 0.000442 ***
## hospitaldischargeyear2013 2.57e-05 ***
## hospitaldischargeyear2014 4.72e-14 ***
## hospitaldischargeyear2015-16 0.001895 **
## dialysis1 < 2e-16 ***
## aids1 < 2e-16 ***
## hepaticfailureTRUE < 2e-16 ***
## diabetes1 < 2e-16 ***
## immunosuppression1 < 2e-16 ***
## leukemia1 < 2e-16 ***
## lymphoma1 < 2e-16 ***
## metastaticcancer1 3.54e-05 ***
## thrombolytics1 < 2e-16 ***
## sofa_respiration_baseline2TRUE < 2e-16 ***
## cardiovascular_baseline1 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 647128 on 638756 degrees of freedom
## Residual deviance: 590208 on 638710 degrees of freedom
## AIC: 590302
##
## Number of Fisher Scoring iterations: 6nrow(ssd_incl_te)## [1] 273752ssd_incl_te$BaselineSepsisPred <- predict(Baseline_Sepsis_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
BaselineSepsis.Pred <- prediction(ssd_incl_te$BaselineSepsisPred, ssd_incl_te$sepsis_outcome)
BaselineSepsis.Perf <- performance(BaselineSepsis.Pred, "tpr", "fpr")
plot(BaselineSepsis.Perf, main = "Baseline Sepsis
Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(BaselineSepsis.Pred,"auc")@y.values[[1]],3))) 
performance(BaselineSepsis.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.7078539
##
##
## Slot "alpha.values":
## list()BaselineSepsis.Pred.roc <- roc(sepsis_outcome~BaselineSepsisPred,data=ssd_incl_te)
try({ci(BaselineSepsis.Pred.roc, conf.level=0.99)},silent=TRUE)## 99% CI: 0.7049-0.7108 (DeLong)ggplot(calibration(as.factor(!sepsis_outcome)~BaselineSepsisPred, data = ssd_incl_te))+ggtitle("Calibration of Baseline Sepsis Prediction")## Warning: Removed 1 rows containing missing values (geom_errorbar).
qplot(BaselineSepsisPred, data = ssd_incl_te)+ggtitle("Histogram of Baseline Sepsis Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
22 Cross validation
partitions the data into 5 groups and then uses the 4 groups to predict the 5th group. It does this 5 times and then takes the average, ROC curves,
SIRS1_ADJ_Sepsis_tr<-glm(sepsis_outcome ~ as.factor(SIRS_total) + age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status + hospital_size + physicianSpeciality2 + hospitaldischargeyear + dialysis + aids + hepaticfailure + diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer + thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline, data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SIRS1_ADJ_Sepsis_tr)
#sjt.glm(SIRS1_ADJ_Sepsis_tr)
#drop1(SIRS1_ADJ_Sepsis_tr,test="Chisq")
summary(SIRS1_ADJ_Sepsis_tr)##
## Call:
## glm(formula = sepsis_outcome ~ as.factor(SIRS_total) + age_Ranges +
## gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status +
## hospital_size + physicianSpeciality2 + hospitaldischargeyear +
## dialysis + aids + hepaticfailure + diabetes + immunosuppression +
## leukemia + lymphoma + metastaticcancer + thrombolytics +
## sofa_respiration_baseline2 + cardiovascular_baseline, family = "binomial",
## data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.1495 -0.7000 -0.4704 -0.2145 3.5849
##
## Coefficients:
## Estimate Std. Error z value
## (Intercept) -2.429719 0.039665 -61.257
## as.factor(SIRS_total)1 0.436152 0.023983 18.186
## as.factor(SIRS_total)2 0.940994 0.022745 41.372
## as.factor(SIRS_total)3 1.609766 0.022686 70.960
## as.factor(SIRS_total)4 2.123455 0.023522 90.276
## age_Ranges(25,35] 0.172778 0.027345 6.318
## age_Ranges(35,45] 0.349355 0.025416 13.745
## age_Ranges(45,55] 0.561817 0.023515 23.892
## age_Ranges(55,65] 0.758603 0.023001 32.981
## age_Ranges(65,75] 0.825533 0.022998 35.895
## age_Ranges(75,85] 0.918961 0.023125 39.738
## age_Ranges(85,100] 1.060331 0.024332 43.578
## gender2Female 0.047199 0.006766 6.976
## gender2Other/Unknown -1.227754 0.268623 -4.571
## ethnicity2African American -0.075559 0.010939 -6.907
## ethnicity2Hispanic 0.423319 0.015132 27.976
## ethnicity2Asian 0.077548 0.029551 2.624
## ethnicity2Native American 0.299836 0.037605 7.973
## ethnicity2Other/Unknown 0.074933 0.014816 5.058
## BMI_Ranges(18.5,25] -0.223233 0.015089 -14.795
## BMI_Ranges(25,35] -0.287623 0.014782 -19.457
## BMI_Ranges(35,200] -0.087281 0.016028 -5.445
## BMI_RangesOther/Unknown -0.474443 0.023598 -20.106
## icu_admit_source2OR/Proc Area -2.013520 0.014539 -138.490
## icu_admit_source2Direct Admit -0.545531 0.012789 -42.657
## icu_admit_source2Emergency Department -0.231184 0.008369 -27.623
## icu_admit_source2Other -0.210439 0.033315 -6.317
## icu_admit_source2Step-Down Unit -0.007810 0.021107 -0.370
## hospital_teaching_statusf -0.244631 0.024645 -9.926
## hospital_teaching_statust -0.207217 0.024870 -8.332
## hospital_size<100 0.667845 0.023520 28.395
## hospital_size100-249 0.333243 0.019163 17.390
## hospital_size250-500 0.254919 0.019497 13.075
## hospital_size>500 0.119283 0.018237 6.541
## physicianSpeciality2Speciality-Other -0.517197 0.007584 -68.200
## hospitaldischargeyear2011 0.086893 0.013067 6.650
## hospitaldischargeyear2012 -0.057270 0.012681 -4.516
## hospitaldischargeyear2013 -0.056253 0.012392 -4.539
## hospitaldischargeyear2014 -0.078709 0.012296 -6.401
## hospitaldischargeyear2015-16 -0.040295 0.012168 -3.311
## dialysis1 0.280215 0.017545 15.972
## aids1 1.262548 0.087496 14.430
## hepaticfailureTRUE 0.166797 0.021570 7.733
## diabetes1 -0.064800 0.008329 -7.780
## immunosuppression1 0.512198 0.020312 25.217
## leukemia1 0.332608 0.033869 9.821
## lymphoma1 0.335520 0.046166 7.268
## metastaticcancer1 0.035127 0.024025 1.462
## thrombolytics1 -2.191144 0.060462 -36.240
## sofa_respiration_baseline2TRUE 0.447371 0.007468 59.904
## cardiovascular_baseline1 -0.012943 0.008184 -1.581
## Pr(>|z|)
## (Intercept) < 2e-16 ***
## as.factor(SIRS_total)1 < 2e-16 ***
## as.factor(SIRS_total)2 < 2e-16 ***
## as.factor(SIRS_total)3 < 2e-16 ***
## as.factor(SIRS_total)4 < 2e-16 ***
## age_Ranges(25,35] 2.64e-10 ***
## age_Ranges(35,45] < 2e-16 ***
## age_Ranges(45,55] < 2e-16 ***
## age_Ranges(55,65] < 2e-16 ***
## age_Ranges(65,75] < 2e-16 ***
## age_Ranges(75,85] < 2e-16 ***
## age_Ranges(85,100] < 2e-16 ***
## gender2Female 3.03e-12 ***
## gender2Other/Unknown 4.86e-06 ***
## ethnicity2African American 4.95e-12 ***
## ethnicity2Hispanic < 2e-16 ***
## ethnicity2Asian 0.008685 **
## ethnicity2Native American 1.54e-15 ***
## ethnicity2Other/Unknown 4.24e-07 ***
## BMI_Ranges(18.5,25] < 2e-16 ***
## BMI_Ranges(25,35] < 2e-16 ***
## BMI_Ranges(35,200] 5.17e-08 ***
## BMI_RangesOther/Unknown < 2e-16 ***
## icu_admit_source2OR/Proc Area < 2e-16 ***
## icu_admit_source2Direct Admit < 2e-16 ***
## icu_admit_source2Emergency Department < 2e-16 ***
## icu_admit_source2Other 2.67e-10 ***
## icu_admit_source2Step-Down Unit 0.711369
## hospital_teaching_statusf < 2e-16 ***
## hospital_teaching_statust < 2e-16 ***
## hospital_size<100 < 2e-16 ***
## hospital_size100-249 < 2e-16 ***
## hospital_size250-500 < 2e-16 ***
## hospital_size>500 6.12e-11 ***
## physicianSpeciality2Speciality-Other < 2e-16 ***
## hospitaldischargeyear2011 2.94e-11 ***
## hospitaldischargeyear2012 6.29e-06 ***
## hospitaldischargeyear2013 5.64e-06 ***
## hospitaldischargeyear2014 1.54e-10 ***
## hospitaldischargeyear2015-16 0.000928 ***
## dialysis1 < 2e-16 ***
## aids1 < 2e-16 ***
## hepaticfailureTRUE 1.05e-14 ***
## diabetes1 7.28e-15 ***
## immunosuppression1 < 2e-16 ***
## leukemia1 < 2e-16 ***
## lymphoma1 3.66e-13 ***
## metastaticcancer1 0.143703
## thrombolytics1 < 2e-16 ***
## sofa_respiration_baseline2TRUE < 2e-16 ***
## cardiovascular_baseline1 0.113769
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 647128 on 638756 degrees of freedom
## Residual deviance: 560649 on 638706 degrees of freedom
## AIC: 560751
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$SIRS1ADJSepsisPred <- predict(SIRS1_ADJ_Sepsis_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
SIRS1ADJSepsis.Pred <- prediction(ssd_incl_te$SIRS1ADJSepsisPred, ssd_incl_te$sepsis_outcome)
SIRS1ADJSepsis.Perf <- performance(SIRS1ADJSepsis.Pred, "tpr", "fpr")
plot(SIRS1ADJSepsis.Perf, main = "SIRS Total Adjusted
Sepsis Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SIRS1ADJSepsis.Pred,"auc")@y.values[[1]],3))) 
performance(SIRS1ADJSepsis.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.7553989
##
##
## Slot "alpha.values":
## list()SIRS1ADJSepsis.Pred.roc <- roc(sepsis_outcome~SIRS1ADJSepsisPred,data=ssd_incl_te)
ci(SIRS1ADJSepsis.Pred.roc, conf.level=0.99)## 99% CI: 0.7526-0.7582 (DeLong)ggplot(calibration(as.factor(!sepsis_outcome)~SIRS1ADJSepsisPred, data = ssd_incl_te))+ggtitle("Calibration of SIRS Total Sepsis Prediction")## Warning: Removed 1 rows containing missing values (geom_errorbar).
qplot(SIRS1ADJSepsisPred, data = ssd_incl_te)+ggtitle("Histogram of SIRS Total Sepsis Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
SIRS2_ADJ_Sepsis_tr<-glm(sepsis_outcome ~ as.factor(SIRS_Positive) + age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status + hospital_size + physicianSpeciality2 + hospitaldischargeyear + dialysis + aids + hepaticfailure + diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer + thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline, data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SIRS2_ADJ_Sepsis_tr)
#sjt.glm(SIRS2_ADJ_Sepsis_tr)
#drop1(SIRS2_ADJ_Sepsis_tr,test="Chisq")
summary(SIRS2_ADJ_Sepsis_tr)##
## Call:
## glm(formula = sepsis_outcome ~ as.factor(SIRS_Positive) + age_Ranges +
## gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status +
## hospital_size + physicianSpeciality2 + hospitaldischargeyear +
## dialysis + aids + hepaticfailure + diabetes + immunosuppression +
## leukemia + lymphoma + metastaticcancer + thrombolytics +
## sofa_respiration_baseline2 + cardiovascular_baseline, family = "binomial",
## data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.9803 -0.7421 -0.4828 -0.2363 3.5802
##
## Coefficients:
## Estimate Std. Error z value
## (Intercept) -1.936435 0.033653 -57.542
## as.factor(SIRS_Positive)TRUE 1.048040 0.009609 109.071
## age_Ranges(25,35] 0.162463 0.026974 6.023
## age_Ranges(35,45] 0.327205 0.025070 13.052
## age_Ranges(45,55] 0.530769 0.023195 22.883
## age_Ranges(55,65] 0.730340 0.022688 32.191
## age_Ranges(65,75] 0.789052 0.022681 34.790
## age_Ranges(75,85] 0.874976 0.022801 38.374
## age_Ranges(85,100] 1.002089 0.023981 41.787
## gender2Female 0.044010 0.006658 6.610
## gender2Other/Unknown -1.004654 0.264674 -3.796
## ethnicity2African American -0.092363 0.010769 -8.577
## ethnicity2Hispanic 0.414171 0.014891 27.813
## ethnicity2Asian 0.085743 0.029042 2.952
## ethnicity2Native American 0.317633 0.036965 8.593
## ethnicity2Other/Unknown 0.082246 0.014582 5.640
## BMI_Ranges(18.5,25] -0.232734 0.014828 -15.695
## BMI_Ranges(25,35] -0.300477 0.014528 -20.682
## BMI_Ranges(35,200] -0.099830 0.015759 -6.335
## BMI_RangesOther/Unknown -0.524068 0.023235 -22.555
## icu_admit_source2OR/Proc Area -1.959456 0.014380 -136.259
## icu_admit_source2Direct Admit -0.558916 0.012569 -44.469
## icu_admit_source2Emergency Department -0.271484 0.008222 -33.021
## icu_admit_source2Other -0.190686 0.032700 -5.831
## icu_admit_source2Step-Down Unit 0.017408 0.020719 0.840
## hospital_teaching_statusf -0.253374 0.024258 -10.445
## hospital_teaching_statust -0.211064 0.024432 -8.639
## hospital_size<100 0.612993 0.023172 26.455
## hospital_size100-249 0.324457 0.018871 17.194
## hospital_size250-500 0.284720 0.019202 14.828
## hospital_size>500 0.150109 0.017929 8.373
## physicianSpeciality2Speciality-Other -0.573496 0.007451 -76.974
## hospitaldischargeyear2011 0.085237 0.012839 6.639
## hospitaldischargeyear2012 -0.065207 0.012465 -5.231
## hospitaldischargeyear2013 -0.077513 0.012183 -6.362
## hospitaldischargeyear2014 -0.108178 0.012091 -8.947
## hospitaldischargeyear2015-16 -0.066888 0.011965 -5.591
## dialysis1 0.265450 0.017262 15.378
## aids1 1.314977 0.085993 15.292
## hepaticfailureTRUE 0.168457 0.021192 7.949
## diabetes1 -0.071153 0.008198 -8.679
## immunosuppression1 0.549108 0.019920 27.565
## leukemia1 0.436945 0.033120 13.193
## lymphoma1 0.379458 0.045234 8.389
## metastaticcancer1 0.053638 0.023601 2.273
## thrombolytics1 -2.158174 0.060174 -35.866
## sofa_respiration_baseline2TRUE 0.433702 0.007344 59.057
## cardiovascular_baseline1 -0.040490 0.008057 -5.025
## Pr(>|z|)
## (Intercept) < 2e-16 ***
## as.factor(SIRS_Positive)TRUE < 2e-16 ***
## age_Ranges(25,35] 1.71e-09 ***
## age_Ranges(35,45] < 2e-16 ***
## age_Ranges(45,55] < 2e-16 ***
## age_Ranges(55,65] < 2e-16 ***
## age_Ranges(65,75] < 2e-16 ***
## age_Ranges(75,85] < 2e-16 ***
## age_Ranges(85,100] < 2e-16 ***
## gender2Female 3.85e-11 ***
## gender2Other/Unknown 0.000147 ***
## ethnicity2African American < 2e-16 ***
## ethnicity2Hispanic < 2e-16 ***
## ethnicity2Asian 0.003153 **
## ethnicity2Native American < 2e-16 ***
## ethnicity2Other/Unknown 1.70e-08 ***
## BMI_Ranges(18.5,25] < 2e-16 ***
## BMI_Ranges(25,35] < 2e-16 ***
## BMI_Ranges(35,200] 2.38e-10 ***
## BMI_RangesOther/Unknown < 2e-16 ***
## icu_admit_source2OR/Proc Area < 2e-16 ***
## icu_admit_source2Direct Admit < 2e-16 ***
## icu_admit_source2Emergency Department < 2e-16 ***
## icu_admit_source2Other 5.50e-09 ***
## icu_admit_source2Step-Down Unit 0.400795
## hospital_teaching_statusf < 2e-16 ***
## hospital_teaching_statust < 2e-16 ***
## hospital_size<100 < 2e-16 ***
## hospital_size100-249 < 2e-16 ***
## hospital_size250-500 < 2e-16 ***
## hospital_size>500 < 2e-16 ***
## physicianSpeciality2Speciality-Other < 2e-16 ***
## hospitaldischargeyear2011 3.16e-11 ***
## hospitaldischargeyear2012 1.68e-07 ***
## hospitaldischargeyear2013 1.99e-10 ***
## hospitaldischargeyear2014 < 2e-16 ***
## hospitaldischargeyear2015-16 2.26e-08 ***
## dialysis1 < 2e-16 ***
## aids1 < 2e-16 ***
## hepaticfailureTRUE 1.88e-15 ***
## diabetes1 < 2e-16 ***
## immunosuppression1 < 2e-16 ***
## leukemia1 < 2e-16 ***
## lymphoma1 < 2e-16 ***
## metastaticcancer1 0.023046 *
## thrombolytics1 < 2e-16 ***
## sofa_respiration_baseline2TRUE < 2e-16 ***
## cardiovascular_baseline1 5.02e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 647128 on 638756 degrees of freedom
## Residual deviance: 576168 on 638709 degrees of freedom
## AIC: 576264
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$SIRS2ADJSepsisPred <- predict(SIRS2_ADJ_Sepsis_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
SIRS2ADJSepsis.Pred <- prediction(ssd_incl_te$SIRS2ADJSepsisPred, ssd_incl_te$sepsis_outcome)
SIRS2ADJSepsis.Perf <- performance(SIRS2ADJSepsis.Pred, "tpr", "fpr")
plot(SIRS2ADJSepsis.Perf, main = "SIRS Positive Adjusted
Sepsis Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SIRS2ADJSepsis.Pred,"auc")@y.values[[1]],3))) 
performance(SIRS2ADJSepsis.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.7303764
##
##
## Slot "alpha.values":
## list()SIRS2ADJSepsis.Pred.roc <- roc(sepsis_outcome~SIRS2ADJSepsisPred,data=ssd_incl_te)
ci(SIRS2ADJSepsis.Pred.roc, conf.level=0.99)## 99% CI: 0.7275-0.7332 (DeLong)ggplot(calibration(as.factor(!sepsis_outcome)~SIRS2ADJSepsisPred, data = ssd_incl_te))+ggtitle("Calibration of SIRS Positive Sepsis Prediction")## Warning: Removed 1 rows containing missing values (geom_errorbar).
qplot(SIRS2ADJSepsisPred, data = ssd_incl_te)+ggtitle("Histogram of SIRS Positive Sepsis Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
qSOFA1_ADJ_Sepsis_tr<-glm(sepsis_outcome ~ as.factor(qSOFA_total) + age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status + hospital_size + physicianSpeciality2 + hospitaldischargeyear + dialysis + aids + hepaticfailure + diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer + thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline, data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(qSOFA1_ADJ_Sepsis_tr)
#sjt.glm(qSOFA1_ADJ_Sepsis_tr)
#drop1(qSOFA1_ADJ_Sepsis_tr,test="Chisq")
summary(qSOFA1_ADJ_Sepsis_tr)##
## Call:
## glm(formula = sepsis_outcome ~ as.factor(qSOFA_total) + age_Ranges +
## gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status +
## hospital_size + physicianSpeciality2 + hospitaldischargeyear +
## dialysis + aids + hepaticfailure + diabetes + immunosuppression +
## leukemia + lymphoma + metastaticcancer + thrombolytics +
## sofa_respiration_baseline2 + cardiovascular_baseline, family = "binomial",
## data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.1636 -0.7142 -0.4937 -0.2294 3.4145
##
## Coefficients:
## Estimate Std. Error z value
## (Intercept) -2.210126 0.037877 -58.349
## as.factor(qSOFA_total)1 0.644273 0.020786 30.996
## as.factor(qSOFA_total)2 1.163153 0.020020 58.098
## as.factor(qSOFA_total)3 1.772241 0.020300 87.301
## age_Ranges(25,35] 0.167541 0.027182 6.164
## age_Ranges(35,45] 0.307748 0.025266 12.180
## age_Ranges(45,55] 0.463480 0.023372 19.830
## age_Ranges(55,65] 0.637824 0.022859 27.902
## age_Ranges(65,75] 0.675474 0.022849 29.563
## age_Ranges(75,85] 0.729479 0.022964 31.767
## age_Ranges(85,100] 0.808471 0.024149 33.479
## gender2Female 0.031488 0.006702 4.698
## gender2Other/Unknown -1.048583 0.266049 -3.941
## ethnicity2African American -0.056398 0.010855 -5.195
## ethnicity2Hispanic 0.442768 0.014988 29.541
## ethnicity2Asian 0.088790 0.029224 3.038
## ethnicity2Native American 0.269451 0.037163 7.251
## ethnicity2Other/Unknown 0.098057 0.014689 6.675
## BMI_Ranges(18.5,25] -0.213684 0.014944 -14.299
## BMI_Ranges(25,35] -0.259585 0.014649 -17.721
## BMI_Ranges(35,200] -0.059729 0.015896 -3.758
## BMI_RangesOther/Unknown -0.518174 0.023360 -22.182
## icu_admit_source2OR/Proc Area -1.897887 0.014444 -131.398
## icu_admit_source2Direct Admit -0.543341 0.012658 -42.925
## icu_admit_source2Emergency Department -0.260007 0.008287 -31.376
## icu_admit_source2Other -0.205693 0.032990 -6.235
## icu_admit_source2Step-Down Unit 0.002663 0.020917 0.127
## hospital_teaching_statusf -0.336939 0.024412 -13.802
## hospital_teaching_statust -0.305396 0.024511 -12.459
## hospital_size<100 0.775406 0.023350 33.208
## hospital_size100-249 0.444667 0.019011 23.391
## hospital_size250-500 0.390689 0.019337 20.205
## hospital_size>500 0.230553 0.017992 12.814
## physicianSpeciality2Speciality-Other -0.534023 0.007509 -71.116
## hospitaldischargeyear2011 0.064268 0.012930 4.970
## hospitaldischargeyear2012 -0.105120 0.012561 -8.369
## hospitaldischargeyear2013 -0.105697 0.012273 -8.612
## hospitaldischargeyear2014 -0.133086 0.012179 -10.928
## hospitaldischargeyear2015-16 -0.098864 0.012056 -8.200
## dialysis1 0.234254 0.017422 13.446
## aids1 1.322708 0.086976 15.208
## hepaticfailureTRUE 0.099746 0.021374 4.667
## diabetes1 -0.050246 0.008274 -6.073
## immunosuppression1 0.619986 0.020126 30.806
## leukemia1 0.501722 0.033508 14.973
## lymphoma1 0.414851 0.045777 9.062
## metastaticcancer1 0.075231 0.023838 3.156
## thrombolytics1 -2.156666 0.060254 -35.793
## sofa_respiration_baseline2TRUE 0.451352 0.007391 61.071
## cardiovascular_baseline1 -0.075059 0.008102 -9.265
## Pr(>|z|)
## (Intercept) < 2e-16 ***
## as.factor(qSOFA_total)1 < 2e-16 ***
## as.factor(qSOFA_total)2 < 2e-16 ***
## as.factor(qSOFA_total)3 < 2e-16 ***
## age_Ranges(25,35] 7.11e-10 ***
## age_Ranges(35,45] < 2e-16 ***
## age_Ranges(45,55] < 2e-16 ***
## age_Ranges(55,65] < 2e-16 ***
## age_Ranges(65,75] < 2e-16 ***
## age_Ranges(75,85] < 2e-16 ***
## age_Ranges(85,100] < 2e-16 ***
## gender2Female 2.62e-06 ***
## gender2Other/Unknown 8.10e-05 ***
## ethnicity2African American 2.04e-07 ***
## ethnicity2Hispanic < 2e-16 ***
## ethnicity2Asian 0.002380 **
## ethnicity2Native American 4.15e-13 ***
## ethnicity2Other/Unknown 2.47e-11 ***
## BMI_Ranges(18.5,25] < 2e-16 ***
## BMI_Ranges(25,35] < 2e-16 ***
## BMI_Ranges(35,200] 0.000172 ***
## BMI_RangesOther/Unknown < 2e-16 ***
## icu_admit_source2OR/Proc Area < 2e-16 ***
## icu_admit_source2Direct Admit < 2e-16 ***
## icu_admit_source2Emergency Department < 2e-16 ***
## icu_admit_source2Other 4.52e-10 ***
## icu_admit_source2Step-Down Unit 0.898706
## hospital_teaching_statusf < 2e-16 ***
## hospital_teaching_statust < 2e-16 ***
## hospital_size<100 < 2e-16 ***
## hospital_size100-249 < 2e-16 ***
## hospital_size250-500 < 2e-16 ***
## hospital_size>500 < 2e-16 ***
## physicianSpeciality2Speciality-Other < 2e-16 ***
## hospitaldischargeyear2011 6.68e-07 ***
## hospitaldischargeyear2012 < 2e-16 ***
## hospitaldischargeyear2013 < 2e-16 ***
## hospitaldischargeyear2014 < 2e-16 ***
## hospitaldischargeyear2015-16 2.40e-16 ***
## dialysis1 < 2e-16 ***
## aids1 < 2e-16 ***
## hepaticfailureTRUE 3.06e-06 ***
## diabetes1 1.26e-09 ***
## immunosuppression1 < 2e-16 ***
## leukemia1 < 2e-16 ***
## lymphoma1 < 2e-16 ***
## metastaticcancer1 0.001600 **
## thrombolytics1 < 2e-16 ***
## sofa_respiration_baseline2TRUE < 2e-16 ***
## cardiovascular_baseline1 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 647128 on 638756 degrees of freedom
## Residual deviance: 570280 on 638707 degrees of freedom
## AIC: 570380
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$qSOFA1ADJSepsisPred <- predict(qSOFA1_ADJ_Sepsis_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
qSOFA1ADJSepsis.Pred <- prediction(ssd_incl_te$qSOFA1ADJSepsisPred, ssd_incl_te$sepsis_outcome)
qSOFA1ADJSepsis.Perf <- performance(qSOFA1ADJSepsis.Pred, "tpr", "fpr")
plot(qSOFA1ADJSepsis.Perf, main = "qSOFA1 Total Adjusted
Sepsis Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(qSOFA1ADJSepsis.Pred,"auc")@y.values[[1]],3))) 
performance(qSOFA1ADJSepsis.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.7409462
##
##
## Slot "alpha.values":
## list()qSOFA1ADJSepsis.Pred.roc <- roc(sepsis_outcome~qSOFA1ADJSepsisPred,data=ssd_incl_te)
ci(qSOFA1ADJSepsis.Pred.roc, conf.level=0.99)## 99% CI: 0.7381-0.7438 (DeLong)ggplot(calibration(as.factor(!sepsis_outcome)~qSOFA1ADJSepsisPred, data = ssd_incl_te))+ggtitle("Calibration of qSOFA Total Sepsis Prediction")## Warning: Removed 1 rows containing missing values (geom_errorbar).
qplot(qSOFA1ADJSepsisPred, data = ssd_incl_te)+ggtitle("Histogram of qSOFA Total Sepsis Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
qSOFA2_ADJ_Sepsis_tr<-glm(sepsis_outcome ~ as.factor(qSOFA_Positive) + age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status + hospital_size + physicianSpeciality2 + hospitaldischargeyear + dialysis + aids + hepaticfailure + diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer + thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline, data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(qSOFA2_ADJ_Sepsis_tr)
#sjt.glm(qSOFA2_ADJ_Sepsis_tr)
#drop1(qSOFA2_ADJ_Sepsis_tr,test="Chisq")
summary(qSOFA2_ADJ_Sepsis_tr)##
## Call:
## glm(formula = sepsis_outcome ~ as.factor(qSOFA_Positive) + age_Ranges +
## gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status +
## hospital_size + physicianSpeciality2 + hospitaldischargeyear +
## dialysis + aids + hepaticfailure + diabetes + immunosuppression +
## leukemia + lymphoma + metastaticcancer + thrombolytics +
## sofa_respiration_baseline2 + cardiovascular_baseline, family = "binomial",
## data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.0393 -0.7351 -0.4970 -0.2318 3.4675
##
## Coefficients:
## Estimate Std. Error z value
## (Intercept) -1.613432 0.033040 -48.833
## as.factor(qSOFA_Positive)TRUE 0.858277 0.008067 106.392
## age_Ranges(25,35] 0.166693 0.027053 6.162
## age_Ranges(35,45] 0.309178 0.025142 12.297
## age_Ranges(45,55] 0.467968 0.023255 20.124
## age_Ranges(55,65] 0.647344 0.022744 28.463
## age_Ranges(65,75] 0.689490 0.022732 30.331
## age_Ranges(75,85] 0.755401 0.022845 33.067
## age_Ranges(85,100] 0.860668 0.024010 35.846
## gender2Female 0.034811 0.006652 5.233
## gender2Other/Unknown -0.987923 0.264232 -3.739
## ethnicity2African American -0.057522 0.010779 -5.336
## ethnicity2Hispanic 0.429726 0.014880 28.879
## ethnicity2Asian 0.082931 0.028990 2.861
## ethnicity2Native American 0.295288 0.036883 8.006
## ethnicity2Other/Unknown 0.097719 0.014576 6.704
## BMI_Ranges(18.5,25] -0.233284 0.014814 -15.748
## BMI_Ranges(25,35] -0.294022 0.014518 -20.252
## BMI_Ranges(35,200] -0.089909 0.015757 -5.706
## BMI_RangesOther/Unknown -0.549213 0.023181 -23.692
## icu_admit_source2OR/Proc Area -1.926253 0.014386 -133.902
## icu_admit_source2Direct Admit -0.568880 0.012550 -45.330
## icu_admit_source2Emergency Department -0.281458 0.008214 -34.267
## icu_admit_source2Other -0.195166 0.032709 -5.967
## icu_admit_source2Step-Down Unit 0.012350 0.020723 0.596
## hospital_teaching_statusf -0.327672 0.024226 -13.526
## hospital_teaching_statust -0.291603 0.024332 -11.984
## hospital_size<100 0.713440 0.023164 30.800
## hospital_size100-249 0.406885 0.018854 21.581
## hospital_size250-500 0.377611 0.019187 19.680
## hospital_size>500 0.222832 0.017857 12.479
## physicianSpeciality2Speciality-Other -0.574583 0.007441 -77.215
## hospitaldischargeyear2011 0.072656 0.012825 5.665
## hospitaldischargeyear2012 -0.089982 0.012458 -7.223
## hospitaldischargeyear2013 -0.098500 0.012175 -8.090
## hospitaldischargeyear2014 -0.126439 0.012083 -10.464
## hospitaldischargeyear2015-16 -0.080106 0.011959 -6.699
## dialysis1 0.244431 0.017266 14.157
## aids1 1.316464 0.086323 15.250
## hepaticfailureTRUE 0.133771 0.021190 6.313
## diabetes1 -0.057409 0.008208 -6.994
## immunosuppression1 0.594927 0.019985 29.768
## leukemia1 0.493029 0.033257 14.825
## lymphoma1 0.402676 0.045354 8.878
## metastaticcancer1 0.076569 0.023661 3.236
## thrombolytics1 -2.190913 0.060142 -36.429
## sofa_respiration_baseline2TRUE 0.460443 0.007332 62.796
## cardiovascular_baseline1 -0.081378 0.008038 -10.125
## Pr(>|z|)
## (Intercept) < 2e-16 ***
## as.factor(qSOFA_Positive)TRUE < 2e-16 ***
## age_Ranges(25,35] 7.19e-10 ***
## age_Ranges(35,45] < 2e-16 ***
## age_Ranges(45,55] < 2e-16 ***
## age_Ranges(55,65] < 2e-16 ***
## age_Ranges(65,75] < 2e-16 ***
## age_Ranges(75,85] < 2e-16 ***
## age_Ranges(85,100] < 2e-16 ***
## gender2Female 1.67e-07 ***
## gender2Other/Unknown 0.000185 ***
## ethnicity2African American 9.48e-08 ***
## ethnicity2Hispanic < 2e-16 ***
## ethnicity2Asian 0.004227 **
## ethnicity2Native American 1.18e-15 ***
## ethnicity2Other/Unknown 2.02e-11 ***
## BMI_Ranges(18.5,25] < 2e-16 ***
## BMI_Ranges(25,35] < 2e-16 ***
## BMI_Ranges(35,200] 1.16e-08 ***
## BMI_RangesOther/Unknown < 2e-16 ***
## icu_admit_source2OR/Proc Area < 2e-16 ***
## icu_admit_source2Direct Admit < 2e-16 ***
## icu_admit_source2Emergency Department < 2e-16 ***
## icu_admit_source2Other 2.42e-09 ***
## icu_admit_source2Step-Down Unit 0.551192
## hospital_teaching_statusf < 2e-16 ***
## hospital_teaching_statust < 2e-16 ***
## hospital_size<100 < 2e-16 ***
## hospital_size100-249 < 2e-16 ***
## hospital_size250-500 < 2e-16 ***
## hospital_size>500 < 2e-16 ***
## physicianSpeciality2Speciality-Other < 2e-16 ***
## hospitaldischargeyear2011 1.47e-08 ***
## hospitaldischargeyear2012 5.08e-13 ***
## hospitaldischargeyear2013 5.95e-16 ***
## hospitaldischargeyear2014 < 2e-16 ***
## hospitaldischargeyear2015-16 2.11e-11 ***
## dialysis1 < 2e-16 ***
## aids1 < 2e-16 ***
## hepaticfailureTRUE 2.74e-10 ***
## diabetes1 2.67e-12 ***
## immunosuppression1 < 2e-16 ***
## leukemia1 < 2e-16 ***
## lymphoma1 < 2e-16 ***
## metastaticcancer1 0.001212 **
## thrombolytics1 < 2e-16 ***
## sofa_respiration_baseline2TRUE < 2e-16 ***
## cardiovascular_baseline1 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 647128 on 638756 degrees of freedom
## Residual deviance: 577744 on 638709 degrees of freedom
## AIC: 577840
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$qSOFA2ADJSepsisPred <- predict(qSOFA2_ADJ_Sepsis_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
qSOFA2ADJSepsis.Pred <- prediction(ssd_incl_te$qSOFA2ADJSepsisPred, ssd_incl_te$sepsis_outcome)
qSOFA2ADJSepsis.Perf <- performance(qSOFA2ADJSepsis.Pred, "tpr", "fpr")
plot(qSOFA2ADJSepsis.Perf, main = "qSOFA Positive Adjusted
Sepsis Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(qSOFA2ADJSepsis.Pred,"auc")@y.values[[1]],3))) 
performance(qSOFA2ADJSepsis.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.7291955
##
##
## Slot "alpha.values":
## list()qSOFA2ADJSepsis.Pred.roc <- roc(sepsis_outcome~qSOFA2ADJSepsisPred,data=ssd_incl_te)
ci(qSOFA2ADJSepsis.Pred.roc, conf.level=0.99)## 99% CI: 0.7263-0.7321 (DeLong)ggplot(calibration(as.factor(!sepsis_outcome)~qSOFA2ADJSepsisPred, data = ssd_incl_te))+ggtitle("Calibration of qSOFA Positive Sepsis Prediction")## Warning: Removed 1 rows containing missing values (geom_errorbar).
qplot(qSOFA2ADJSepsisPred, data = ssd_incl_te)+ggtitle("Histogram of qSOFA Positive Sepsis Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
SOFA1_ADJ_Sepsis_tr<-glm(sepsis_outcome ~ as.factor(SOFA_Change) + age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status + hospital_size + physicianSpeciality2 + hospitaldischargeyear + dialysis + aids + hepaticfailure + diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer + thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline, data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SOFA1_ADJ_Sepsis_tr)
#sjt.glm(SOFA1_ADJ_Sepsis_tr)
#drop1(SOFA1_ADJ_Sepsis_tr,test="Chisq")
summary(SOFA1_ADJ_Sepsis_tr)##
## Call:
## glm(formula = sepsis_outcome ~ as.factor(SOFA_Change) + age_Ranges +
## gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status +
## hospital_size + physicianSpeciality2 + hospitaldischargeyear +
## dialysis + aids + hepaticfailure + diabetes + immunosuppression +
## leukemia + lymphoma + metastaticcancer + thrombolytics +
## sofa_respiration_baseline2 + cardiovascular_baseline, family = "binomial",
## data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.1484 -0.6904 -0.4485 -0.1961 3.6099
##
## Coefficients:
## Estimate Std. Error z value
## (Intercept) -2.2974474 0.0374927 -61.277
## as.factor(SOFA_Change) 1 0.3815506 0.0195444 19.522
## as.factor(SOFA_Change) 2 0.7749043 0.0198496 39.039
## as.factor(SOFA_Change) 3 1.1701393 0.0196310 59.607
## as.factor(SOFA_Change) 4 1.3627618 0.0197353 69.052
## as.factor(SOFA_Change) 5 1.5448495 0.0201691 76.595
## as.factor(SOFA_Change) 6 1.8229743 0.0209532 87.002
## as.factor(SOFA_Change) 7 1.9324285 0.0217400 88.888
## as.factor(SOFA_Change) 8 2.0646047 0.0233577 88.391
## as.factor(SOFA_Change) 9 2.2093509 0.0254045 86.967
## as.factor(SOFA_Change)10 2.3112344 0.0280222 82.479
## as.factor(SOFA_Change)11 2.3462752 0.0312230 75.146
## as.factor(SOFA_Change)12 2.4894621 0.0362115 68.748
## as.factor(SOFA_Change)13 2.6173961 0.0422963 61.882
## as.factor(SOFA_Change)14 2.6895330 0.0511733 52.557
## as.factor(SOFA_Change)15 2.8433938 0.0621335 45.763
## as.factor(SOFA_Change)16 2.9439344 0.0789525 37.287
## as.factor(SOFA_Change)17 2.9272520 0.1085591 26.965
## as.factor(SOFA_Change)[18,23] 3.3159140 0.1113884 29.769
## age_Ranges(25,35] 0.1229100 0.0276502 4.445
## age_Ranges(35,45] 0.2329097 0.0257154 9.057
## age_Ranges(45,55] 0.3447512 0.0237784 14.499
## age_Ranges(55,65] 0.4805564 0.0232537 20.666
## age_Ranges(65,75] 0.4982811 0.0232423 21.439
## age_Ranges(75,85] 0.5414234 0.0233603 23.177
## age_Ranges(85,100] 0.6497776 0.0245559 26.461
## gender2Female 0.1271904 0.0068417 18.591
## gender2Other/Unknown -1.0727793 0.2680879 -4.002
## ethnicity2African American -0.1476021 0.0110779 -13.324
## ethnicity2Hispanic 0.3656723 0.0152937 23.910
## ethnicity2Asian 0.0024908 0.0298339 0.083
## ethnicity2Native American 0.1088718 0.0380294 2.863
## ethnicity2Other/Unknown 0.0042039 0.0149839 0.281
## BMI_Ranges(18.5,25] -0.2257829 0.0151932 -14.861
## BMI_Ranges(25,35] -0.3092834 0.0148901 -20.771
## BMI_Ranges(35,200] -0.1599401 0.0161740 -9.889
## BMI_RangesOther/Unknown -0.5402381 0.0237741 -22.724
## icu_admit_source2OR/Proc Area -1.9657000 0.0146192 -134.460
## icu_admit_source2Direct Admit -0.5749002 0.0129442 -44.414
## icu_admit_source2Emergency Department -0.2114964 0.0084562 -25.011
## icu_admit_source2Other -0.2096404 0.0336959 -6.222
## icu_admit_source2Step-Down Unit -0.0002818 0.0213110 -0.013
## hospital_teaching_statusf -0.1461240 0.0249314 -5.861
## hospital_teaching_statust -0.1006492 0.0251522 -4.002
## hospital_size<100 0.7137552 0.0237263 30.083
## hospital_size100-249 0.3137806 0.0193616 16.206
## hospital_size250-500 0.2302913 0.0197074 11.686
## hospital_size>500 0.0771523 0.0184306 4.186
## physicianSpeciality2Speciality-Other -0.4624119 0.0076889 -60.140
## hospitaldischargeyear2011 0.0978542 0.0131609 7.435
## hospitaldischargeyear2012 -0.0269191 0.0127768 -2.107
## hospitaldischargeyear2013 -0.0013943 0.0124847 -0.112
## hospitaldischargeyear2014 -0.0355241 0.0123910 -2.867
## hospitaldischargeyear2015-16 -0.0187272 0.0122673 -1.527
## dialysis1 0.4040387 0.0177082 22.816
## aids1 1.2901577 0.0892030 14.463
## hepaticfailureTRUE -0.1266740 0.0216698 -5.846
## diabetes1 -0.0546649 0.0084230 -6.490
## immunosuppression1 0.5625198 0.0206016 27.305
## leukemia1 0.2855345 0.0343888 8.303
## lymphoma1 0.3310231 0.0469236 7.055
## metastaticcancer1 0.0610930 0.0244262 2.501
## thrombolytics1 -2.1415436 0.0608640 -35.186
## sofa_respiration_baseline2TRUE 0.6184497 0.0075956 81.422
## cardiovascular_baseline1 -0.1408438 0.0082414 -17.090
## Pr(>|z|)
## (Intercept) < 2e-16 ***
## as.factor(SOFA_Change) 1 < 2e-16 ***
## as.factor(SOFA_Change) 2 < 2e-16 ***
## as.factor(SOFA_Change) 3 < 2e-16 ***
## as.factor(SOFA_Change) 4 < 2e-16 ***
## as.factor(SOFA_Change) 5 < 2e-16 ***
## as.factor(SOFA_Change) 6 < 2e-16 ***
## as.factor(SOFA_Change) 7 < 2e-16 ***
## as.factor(SOFA_Change) 8 < 2e-16 ***
## as.factor(SOFA_Change) 9 < 2e-16 ***
## as.factor(SOFA_Change)10 < 2e-16 ***
## as.factor(SOFA_Change)11 < 2e-16 ***
## as.factor(SOFA_Change)12 < 2e-16 ***
## as.factor(SOFA_Change)13 < 2e-16 ***
## as.factor(SOFA_Change)14 < 2e-16 ***
## as.factor(SOFA_Change)15 < 2e-16 ***
## as.factor(SOFA_Change)16 < 2e-16 ***
## as.factor(SOFA_Change)17 < 2e-16 ***
## as.factor(SOFA_Change)[18,23] < 2e-16 ***
## age_Ranges(25,35] 8.78e-06 ***
## age_Ranges(35,45] < 2e-16 ***
## age_Ranges(45,55] < 2e-16 ***
## age_Ranges(55,65] < 2e-16 ***
## age_Ranges(65,75] < 2e-16 ***
## age_Ranges(75,85] < 2e-16 ***
## age_Ranges(85,100] < 2e-16 ***
## gender2Female < 2e-16 ***
## gender2Other/Unknown 6.29e-05 ***
## ethnicity2African American < 2e-16 ***
## ethnicity2Hispanic < 2e-16 ***
## ethnicity2Asian 0.93346
## ethnicity2Native American 0.00420 **
## ethnicity2Other/Unknown 0.77905
## BMI_Ranges(18.5,25] < 2e-16 ***
## BMI_Ranges(25,35] < 2e-16 ***
## BMI_Ranges(35,200] < 2e-16 ***
## BMI_RangesOther/Unknown < 2e-16 ***
## icu_admit_source2OR/Proc Area < 2e-16 ***
## icu_admit_source2Direct Admit < 2e-16 ***
## icu_admit_source2Emergency Department < 2e-16 ***
## icu_admit_source2Other 4.92e-10 ***
## icu_admit_source2Step-Down Unit 0.98945
## hospital_teaching_statusf 4.60e-09 ***
## hospital_teaching_statust 6.29e-05 ***
## hospital_size<100 < 2e-16 ***
## hospital_size100-249 < 2e-16 ***
## hospital_size250-500 < 2e-16 ***
## hospital_size>500 2.84e-05 ***
## physicianSpeciality2Speciality-Other < 2e-16 ***
## hospitaldischargeyear2011 1.04e-13 ***
## hospitaldischargeyear2012 0.03513 *
## hospitaldischargeyear2013 0.91108
## hospitaldischargeyear2014 0.00414 **
## hospitaldischargeyear2015-16 0.12686
## dialysis1 < 2e-16 ***
## aids1 < 2e-16 ***
## hepaticfailureTRUE 5.05e-09 ***
## diabetes1 8.59e-11 ***
## immunosuppression1 < 2e-16 ***
## leukemia1 < 2e-16 ***
## lymphoma1 1.73e-12 ***
## metastaticcancer1 0.01238 *
## thrombolytics1 < 2e-16 ***
## sofa_respiration_baseline2TRUE < 2e-16 ***
## cardiovascular_baseline1 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 647128 on 638756 degrees of freedom
## Residual deviance: 551351 on 638692 degrees of freedom
## AIC: 551481
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$SOFA1ADJSepsisPred <- predict(SOFA1_ADJ_Sepsis_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
SOFA1ADJSepsis.Pred <- prediction(ssd_incl_te$SOFA1ADJSepsisPred, ssd_incl_te$sepsis_outcome)
SOFA1ADJSepsis.Perf <- performance(SOFA1ADJSepsis.Pred, "tpr", "fpr")
plot(SOFA1ADJSepsis.Perf, main = "SOFA Continuous Adjusted
Sepsis Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SOFA1ADJSepsis.Pred,"auc")@y.values[[1]],3))) 
performance(SOFA1ADJSepsis.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.7678386
##
##
## Slot "alpha.values":
## list()SOFA1ADJSepsis.Pred.roc <- roc(sepsis_outcome~SOFA1ADJSepsisPred,data=ssd_incl_te)
ci(SOFA1ADJSepsis.Pred.roc, conf.level=0.99)## 99% CI: 0.7651-0.7706 (DeLong)ggplot(calibration(as.factor(!sepsis_outcome)~SOFA1ADJSepsisPred, data = ssd_incl_te))+ggtitle("Calibration of SOFA Total Sepsis Prediction")
qplot(SOFA1ADJSepsisPred, data = ssd_incl_te)+ggtitle("Histogram of SOFA Total Sepsis Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
SOFA2_ADJ_Sepsis_tr<-glm(sepsis_outcome ~ as.factor(SOFA_Positive) + age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status + hospital_size + physicianSpeciality2 + hospitaldischargeyear + dialysis + aids + hepaticfailure + diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer + thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline, data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SOFA2_ADJ_Sepsis_tr)
#sjt.glm(SOFA2_ADJ_Sepsis_tr)
#drop1(SOFA2_ADJ_Sepsis_tr,test="Chisq")
summary(SOFA2_ADJ_Sepsis_tr)##
## Call:
## glm(formula = sepsis_outcome ~ as.factor(SOFA_Positive) + age_Ranges +
## gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status +
## hospital_size + physicianSpeciality2 + hospitaldischargeyear +
## dialysis + aids + hepaticfailure + diabetes + immunosuppression +
## leukemia + lymphoma + metastaticcancer + thrombolytics +
## sofa_respiration_baseline2 + cardiovascular_baseline, family = "binomial",
## data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.0192 -0.7443 -0.4524 -0.2092 3.5876
##
## Coefficients:
## Estimate Std. Error z value
## (Intercept) -1.866539 0.033429 -55.836
## as.factor(SOFA_Positive)TRUE 1.164883 0.008868 131.351
## age_Ranges(25,35] 0.137449 0.027266 5.041
## age_Ranges(35,45] 0.274264 0.025343 10.822
## age_Ranges(45,55] 0.412183 0.023445 17.581
## age_Ranges(55,65] 0.565255 0.022934 24.647
## age_Ranges(65,75] 0.581553 0.022928 25.364
## age_Ranges(75,85] 0.616061 0.023045 26.733
## age_Ranges(85,100] 0.705917 0.024213 29.154
## gender2Female 0.095499 0.006697 14.261
## gender2Other/Unknown -0.942238 0.264427 -3.563
## ethnicity2African American -0.110263 0.010823 -10.188
## ethnicity2Hispanic 0.396282 0.014972 26.468
## ethnicity2Asian 0.046724 0.029111 1.605
## ethnicity2Native American 0.237499 0.037012 6.417
## ethnicity2Other/Unknown 0.054637 0.014656 3.728
## BMI_Ranges(18.5,25] -0.244758 0.014907 -16.419
## BMI_Ranges(25,35] -0.318271 0.014606 -21.790
## BMI_Ranges(35,200] -0.137382 0.015857 -8.664
## BMI_RangesOther/Unknown -0.558014 0.023324 -23.924
## icu_admit_source2OR/Proc Area -1.953553 0.014426 -135.421
## icu_admit_source2Direct Admit -0.571572 0.012627 -45.267
## icu_admit_source2Emergency Department -0.267005 0.008265 -32.306
## icu_admit_source2Other -0.192005 0.032909 -5.834
## icu_admit_source2Step-Down Unit 0.008125 0.020835 0.390
## hospital_teaching_statusf -0.204197 0.024402 -8.368
## hospital_teaching_statust -0.169205 0.024587 -6.882
## hospital_size<100 0.628172 0.023346 26.907
## hospital_size100-249 0.304835 0.018999 16.045
## hospital_size250-500 0.257730 0.019331 13.333
## hospital_size>500 0.111995 0.018061 6.201
## physicianSpeciality2Speciality-Other -0.550969 0.007502 -73.439
## hospitaldischargeyear2011 0.097619 0.012887 7.575
## hospitaldischargeyear2012 -0.034698 0.012515 -2.773
## hospitaldischargeyear2013 -0.021472 0.012235 -1.755
## hospitaldischargeyear2014 -0.054462 0.012142 -4.486
## hospitaldischargeyear2015-16 -0.015746 0.012015 -1.310
## dialysis1 0.315902 0.017433 18.121
## aids1 1.312983 0.086851 15.118
## hepaticfailureTRUE 0.003690 0.021156 0.174
## diabetes1 -0.088014 0.008260 -10.655
## immunosuppression1 0.573149 0.020116 28.492
## leukemia1 0.407810 0.033338 12.233
## lymphoma1 0.379349 0.045566 8.325
## metastaticcancer1 0.074469 0.023833 3.125
## thrombolytics1 -2.080211 0.060319 -34.487
## sofa_respiration_baseline2TRUE 0.516772 0.007399 69.843
## cardiovascular_baseline1 -0.117735 0.008087 -14.559
## Pr(>|z|)
## (Intercept) < 2e-16 ***
## as.factor(SOFA_Positive)TRUE < 2e-16 ***
## age_Ranges(25,35] 4.63e-07 ***
## age_Ranges(35,45] < 2e-16 ***
## age_Ranges(45,55] < 2e-16 ***
## age_Ranges(55,65] < 2e-16 ***
## age_Ranges(65,75] < 2e-16 ***
## age_Ranges(75,85] < 2e-16 ***
## age_Ranges(85,100] < 2e-16 ***
## gender2Female < 2e-16 ***
## gender2Other/Unknown 0.000366 ***
## ethnicity2African American < 2e-16 ***
## ethnicity2Hispanic < 2e-16 ***
## ethnicity2Asian 0.108479
## ethnicity2Native American 1.39e-10 ***
## ethnicity2Other/Unknown 0.000193 ***
## BMI_Ranges(18.5,25] < 2e-16 ***
## BMI_Ranges(25,35] < 2e-16 ***
## BMI_Ranges(35,200] < 2e-16 ***
## BMI_RangesOther/Unknown < 2e-16 ***
## icu_admit_source2OR/Proc Area < 2e-16 ***
## icu_admit_source2Direct Admit < 2e-16 ***
## icu_admit_source2Emergency Department < 2e-16 ***
## icu_admit_source2Other 5.40e-09 ***
## icu_admit_source2Step-Down Unit 0.696569
## hospital_teaching_statusf < 2e-16 ***
## hospital_teaching_statust 5.91e-12 ***
## hospital_size<100 < 2e-16 ***
## hospital_size100-249 < 2e-16 ***
## hospital_size250-500 < 2e-16 ***
## hospital_size>500 5.61e-10 ***
## physicianSpeciality2Speciality-Other < 2e-16 ***
## hospitaldischargeyear2011 3.60e-14 ***
## hospitaldischargeyear2012 0.005562 **
## hospitaldischargeyear2013 0.079263 .
## hospitaldischargeyear2014 7.27e-06 ***
## hospitaldischargeyear2015-16 0.190031
## dialysis1 < 2e-16 ***
## aids1 < 2e-16 ***
## hepaticfailureTRUE 0.861542
## diabetes1 < 2e-16 ***
## immunosuppression1 < 2e-16 ***
## leukemia1 < 2e-16 ***
## lymphoma1 < 2e-16 ***
## metastaticcancer1 0.001781 **
## thrombolytics1 < 2e-16 ***
## sofa_respiration_baseline2TRUE < 2e-16 ***
## cardiovascular_baseline1 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 647128 on 638756 degrees of freedom
## Residual deviance: 569984 on 638709 degrees of freedom
## AIC: 570080
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$SOFA2ADJSepsisPred <- predict(SOFA2_ADJ_Sepsis_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
SOFA2ADJSepsis.Pred <- prediction(ssd_incl_te$SOFA2ADJSepsisPred, ssd_incl_te$sepsis_outcome)
SOFA2ADJSepsis.Perf <- performance(SOFA2ADJSepsis.Pred, "tpr", "fpr")
plot(SOFA2ADJSepsis.Perf, main = "SOFA Positive Adjusted Sepsis Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SOFA2ADJSepsis.Pred,"auc")@y.values[[1]],3))) 
performance(SOFA2ADJSepsis.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.7398636
##
##
## Slot "alpha.values":
## list()SOFA2ADJSepsis.Pred.roc <- roc(sepsis_outcome~SOFA2ADJSepsisPred,data=ssd_incl_te)
ci(SOFA2ADJSepsis.Pred.roc, conf.level=0.99)## 99% CI: 0.7371-0.7427 (DeLong)ggplot(calibration(as.factor(!sepsis_outcome)~SOFA2ADJSepsisPred, data = ssd_incl_te))+ggtitle("Calibration of SOFA Positive Sepsis Prediction")## Warning: Removed 1 rows containing missing values (geom_errorbar).
qplot(SOFA2ADJSepsisPred, data = ssd_incl_te)+ggtitle("Histogram of SOFA Positive Sepsis Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
SOFA Score w/o Baseline SOFA
SOFA3_ADJ_Sepsis_tr<-glm(sepsis_outcome ~ as.factor(SOFA_Positive2) + age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status + hospital_size + physicianSpeciality2 + hospitaldischargeyear + dialysis + aids + hepaticfailure + diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer + thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline, data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SOFA3_ADJ_Sepsis_tr)
#sjt.glm(SOFA3_ADJ_Sepsis_tr)
#drop1(SOFA3_ADJ_Sepsis_tr,test="Chisq")
summary(SOFA3_ADJ_Sepsis_tr)##
## Call:
## glm(formula = sepsis_outcome ~ as.factor(SOFA_Positive2) + age_Ranges +
## gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status +
## hospital_size + physicianSpeciality2 + hospitaldischargeyear +
## dialysis + aids + hepaticfailure + diabetes + immunosuppression +
## leukemia + lymphoma + metastaticcancer + thrombolytics +
## sofa_respiration_baseline2 + cardiovascular_baseline, family = "binomial",
## data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.0136 -0.7503 -0.4458 -0.2054 3.5975
##
## Coefficients:
## Estimate Std. Error z value
## (Intercept) -1.914544 0.033544 -57.076
## as.factor(SOFA_Positive2)TRUE 1.224253 0.009377 130.565
## age_Ranges(25,35] 0.130401 0.027284 4.779
## age_Ranges(35,45] 0.266394 0.025362 10.504
## age_Ranges(45,55] 0.406306 0.023462 17.317
## age_Ranges(55,65] 0.560699 0.022951 24.430
## age_Ranges(65,75] 0.579444 0.022944 25.254
## age_Ranges(75,85] 0.615448 0.023060 26.689
## age_Ranges(85,100] 0.705471 0.024228 29.118
## gender2Female 0.093724 0.006695 14.000
## gender2Other/Unknown -0.960428 0.264839 -3.626
## ethnicity2African American -0.114321 0.010813 -10.572
## ethnicity2Hispanic 0.387527 0.014970 25.887
## ethnicity2Asian 0.045671 0.029083 1.570
## ethnicity2Native American 0.243562 0.036956 6.591
## ethnicity2Other/Unknown 0.052189 0.014652 3.562
## BMI_Ranges(18.5,25] -0.245088 0.014904 -16.445
## BMI_Ranges(25,35] -0.317553 0.014603 -21.745
## BMI_Ranges(35,200] -0.140167 0.015853 -8.841
## BMI_RangesOther/Unknown -0.557646 0.023327 -23.906
## icu_admit_source2OR/Proc Area -1.950075 0.014424 -135.194
## icu_admit_source2Direct Admit -0.569207 0.012622 -45.098
## icu_admit_source2Emergency Department -0.265782 0.008261 -32.173
## icu_admit_source2Other -0.183132 0.032888 -5.568
## icu_admit_source2Step-Down Unit 0.011418 0.020819 0.548
## hospital_teaching_statusf -0.203830 0.024390 -8.357
## hospital_teaching_statust -0.168029 0.024579 -6.836
## hospital_size<100 0.626015 0.023351 26.809
## hospital_size100-249 0.301889 0.018988 15.899
## hospital_size250-500 0.259083 0.019320 13.410
## hospital_size>500 0.110670 0.018054 6.130
## physicianSpeciality2Speciality-Other -0.546170 0.007503 -72.790
## hospitaldischargeyear2011 0.097124 0.012885 7.538
## hospitaldischargeyear2012 -0.034913 0.012512 -2.790
## hospitaldischargeyear2013 -0.024620 0.012231 -2.013
## hospitaldischargeyear2014 -0.056569 0.012138 -4.661
## hospitaldischargeyear2015-16 -0.018383 0.012011 -1.530
## dialysis1 0.028401 0.017084 1.662
## aids1 1.325191 0.086796 15.268
## hepaticfailureTRUE -0.003968 0.021092 -0.188
## diabetes1 -0.086506 0.008253 -10.482
## immunosuppression1 0.568214 0.020114 28.250
## leukemia1 0.414446 0.033304 12.444
## lymphoma1 0.383929 0.045572 8.425
## metastaticcancer1 0.076147 0.023836 3.195
## thrombolytics1 -2.069251 0.060320 -34.305
## sofa_respiration_baseline2TRUE 0.482563 0.007387 65.326
## cardiovascular_baseline1 -0.118644 0.008078 -14.688
## Pr(>|z|)
## (Intercept) < 2e-16 ***
## as.factor(SOFA_Positive2)TRUE < 2e-16 ***
## age_Ranges(25,35] 1.76e-06 ***
## age_Ranges(35,45] < 2e-16 ***
## age_Ranges(45,55] < 2e-16 ***
## age_Ranges(55,65] < 2e-16 ***
## age_Ranges(65,75] < 2e-16 ***
## age_Ranges(75,85] < 2e-16 ***
## age_Ranges(85,100] < 2e-16 ***
## gender2Female < 2e-16 ***
## gender2Other/Unknown 0.000287 ***
## ethnicity2African American < 2e-16 ***
## ethnicity2Hispanic < 2e-16 ***
## ethnicity2Asian 0.116327
## ethnicity2Native American 4.38e-11 ***
## ethnicity2Other/Unknown 0.000368 ***
## BMI_Ranges(18.5,25] < 2e-16 ***
## BMI_Ranges(25,35] < 2e-16 ***
## BMI_Ranges(35,200] < 2e-16 ***
## BMI_RangesOther/Unknown < 2e-16 ***
## icu_admit_source2OR/Proc Area < 2e-16 ***
## icu_admit_source2Direct Admit < 2e-16 ***
## icu_admit_source2Emergency Department < 2e-16 ***
## icu_admit_source2Other 2.57e-08 ***
## icu_admit_source2Step-Down Unit 0.583380
## hospital_teaching_statusf < 2e-16 ***
## hospital_teaching_statust 8.13e-12 ***
## hospital_size<100 < 2e-16 ***
## hospital_size100-249 < 2e-16 ***
## hospital_size250-500 < 2e-16 ***
## hospital_size>500 8.78e-10 ***
## physicianSpeciality2Speciality-Other < 2e-16 ***
## hospitaldischargeyear2011 4.78e-14 ***
## hospitaldischargeyear2012 0.005264 **
## hospitaldischargeyear2013 0.044123 *
## hospitaldischargeyear2014 3.15e-06 ***
## hospitaldischargeyear2015-16 0.125897
## dialysis1 0.096429 .
## aids1 < 2e-16 ***
## hepaticfailureTRUE 0.850790
## diabetes1 < 2e-16 ***
## immunosuppression1 < 2e-16 ***
## leukemia1 < 2e-16 ***
## lymphoma1 < 2e-16 ***
## metastaticcancer1 0.001400 **
## thrombolytics1 < 2e-16 ***
## sofa_respiration_baseline2TRUE < 2e-16 ***
## cardiovascular_baseline1 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 647128 on 638756 degrees of freedom
## Residual deviance: 569775 on 638709 degrees of freedom
## AIC: 569871
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$SOFA3ADJSepsisPred <- predict(SOFA3_ADJ_Sepsis_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
SOFA3ADJSepsis.Pred <- prediction(ssd_incl_te$SOFA3ADJSepsisPred, ssd_incl_te$sepsis_outcome)
SOFA3ADJSepsis.Perf <- performance(SOFA3ADJSepsis.Pred, "tpr", "fpr")
plot(SOFA3ADJSepsis.Perf, main = "SOFA Positive w/o Baseline Adjusted
Sepsis Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SOFA3ADJSepsis.Pred,"auc")@y.values[[1]],3))) 
performance(SOFA3ADJSepsis.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.7393518
##
##
## Slot "alpha.values":
## list()SOFA3ADJSepsis.Pred.roc <- roc(sepsis_outcome~SOFA3ADJSepsisPred,data=ssd_incl_te)
ci(SOFA3ADJSepsis.Pred.roc, conf.level=0.99)## 99% CI: 0.7366-0.7421 (DeLong)ggplot(calibration(as.factor(!sepsis_outcome)~SOFA3ADJSepsisPred, data = ssd_incl_te))+ggtitle("Calibration of SOFA Positive w/o Baseline Sepsis Prediction")## Warning: Removed 1 rows containing missing values (geom_errorbar).
qplot(SOFA3ADJSepsisPred, data = ssd_incl_te)+ggtitle("Histogram of SOFA Positive w/o Baseline Sepsis Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
FuzzyLogic_ADJ_Sepsis_tr<-glm(sepsis_outcome ~ (SepsisFuzzyLogicPositive) + age_Ranges + gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status + hospital_size + physicianSpeciality2 + hospitaldischargeyear + dialysis + aids + hepaticfailure + diabetes + immunosuppression + leukemia + lymphoma + metastaticcancer + thrombolytics + sofa_respiration_baseline2 + cardiovascular_baseline, data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(FuzzyLogic_ADJ_Sepsis_tr)
#sjt.glm(FuzzyLogic_ADJ_Sepsis_tr)
#drop1(FuzzyLogic_ADJ_Sepsis_tr,test="Chisq")
summary(FuzzyLogic_ADJ_Sepsis_tr)##
## Call:
## glm(formula = sepsis_outcome ~ (SepsisFuzzyLogicPositive) + age_Ranges +
## gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status +
## hospital_size + physicianSpeciality2 + hospitaldischargeyear +
## dialysis + aids + hepaticfailure + diabetes + immunosuppression +
## leukemia + lymphoma + metastaticcancer + thrombolytics +
## sofa_respiration_baseline2 + cardiovascular_baseline, family = "binomial",
## data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.0787 -0.7206 -0.4234 -0.1814 3.6169
##
## Coefficients:
## Estimate Std. Error z value
## (Intercept) -2.124152 0.033816 -62.815
## SepsisFuzzyLogicPositiveTRUE 1.494644 0.007929 188.497
## age_Ranges(25,35] 0.200047 0.027507 7.272
## age_Ranges(35,45] 0.380838 0.025582 14.887
## age_Ranges(45,55] 0.539099 0.023648 22.797
## age_Ranges(55,65] 0.710904 0.023120 30.748
## age_Ranges(65,75] 0.744332 0.023110 32.209
## age_Ranges(75,85] 0.822203 0.023233 35.390
## age_Ranges(85,100] 0.957012 0.024461 39.125
## gender2Female 0.036346 0.006828 5.323
## gender2Other/Unknown -1.078963 0.267177 -4.038
## ethnicity2African American -0.029079 0.011073 -2.626
## ethnicity2Hispanic 0.399012 0.015308 26.065
## ethnicity2Asian 0.110971 0.029812 3.722
## ethnicity2Native American 0.266320 0.037867 7.033
## ethnicity2Other/Unknown 0.046935 0.014927 3.144
## BMI_Ranges(18.5,25] -0.220140 0.015229 -14.455
## BMI_Ranges(25,35] -0.286701 0.014915 -19.222
## BMI_Ranges(35,200] -0.114540 0.016172 -7.083
## BMI_RangesOther/Unknown -0.465796 0.023828 -19.548
## icu_admit_source2OR/Proc Area -1.996615 0.014573 -137.012
## icu_admit_source2Direct Admit -0.459874 0.012939 -35.543
## icu_admit_source2Emergency Department -0.280337 0.008454 -33.161
## icu_admit_source2Other -0.107824 0.033765 -3.193
## icu_admit_source2Step-Down Unit 0.055622 0.021391 2.600
## hospital_teaching_statusf -0.240214 0.024886 -9.652
## hospital_teaching_statust -0.207117 0.025137 -8.240
## hospital_size<100 0.621431 0.023826 26.082
## hospital_size100-249 0.311101 0.019367 16.063
## hospital_size250-500 0.262875 0.019696 13.346
## hospital_size>500 0.108788 0.018436 5.901
## physicianSpeciality2Speciality-Other -0.501852 0.007684 -65.313
## hospitaldischargeyear2011 0.092410 0.013172 7.016
## hospitaldischargeyear2012 -0.039503 0.012781 -3.091
## hospitaldischargeyear2013 -0.038688 0.012491 -3.097
## hospitaldischargeyear2014 -0.059266 0.012397 -4.781
## hospitaldischargeyear2015-16 -0.019868 0.012269 -1.619
## dialysis1 0.270859 0.017788 15.227
## aids1 1.331422 0.089546 14.869
## hepaticfailureTRUE -0.029653 0.021485 -1.380
## diabetes1 0.044792 0.008428 5.315
## immunosuppression1 0.526333 0.020537 25.628
## leukemia1 0.399091 0.034129 11.694
## lymphoma1 0.345324 0.046675 7.399
## metastaticcancer1 0.019801 0.024233 0.817
## thrombolytics1 -2.110673 0.060512 -34.880
## sofa_respiration_baseline2TRUE 0.392935 0.007544 52.086
## cardiovascular_baseline1 -0.072916 0.008255 -8.833
## Pr(>|z|)
## (Intercept) < 2e-16 ***
## SepsisFuzzyLogicPositiveTRUE < 2e-16 ***
## age_Ranges(25,35] 3.53e-13 ***
## age_Ranges(35,45] < 2e-16 ***
## age_Ranges(45,55] < 2e-16 ***
## age_Ranges(55,65] < 2e-16 ***
## age_Ranges(65,75] < 2e-16 ***
## age_Ranges(75,85] < 2e-16 ***
## age_Ranges(85,100] < 2e-16 ***
## gender2Female 1.02e-07 ***
## gender2Other/Unknown 5.38e-05 ***
## ethnicity2African American 0.008635 **
## ethnicity2Hispanic < 2e-16 ***
## ethnicity2Asian 0.000197 ***
## ethnicity2Native American 2.02e-12 ***
## ethnicity2Other/Unknown 0.001665 **
## BMI_Ranges(18.5,25] < 2e-16 ***
## BMI_Ranges(25,35] < 2e-16 ***
## BMI_Ranges(35,200] 1.41e-12 ***
## BMI_RangesOther/Unknown < 2e-16 ***
## icu_admit_source2OR/Proc Area < 2e-16 ***
## icu_admit_source2Direct Admit < 2e-16 ***
## icu_admit_source2Emergency Department < 2e-16 ***
## icu_admit_source2Other 0.001406 **
## icu_admit_source2Step-Down Unit 0.009314 **
## hospital_teaching_statusf < 2e-16 ***
## hospital_teaching_statust < 2e-16 ***
## hospital_size<100 < 2e-16 ***
## hospital_size100-249 < 2e-16 ***
## hospital_size250-500 < 2e-16 ***
## hospital_size>500 3.61e-09 ***
## physicianSpeciality2Speciality-Other < 2e-16 ***
## hospitaldischargeyear2011 2.29e-12 ***
## hospitaldischargeyear2012 0.001996 **
## hospitaldischargeyear2013 0.001952 **
## hospitaldischargeyear2014 1.75e-06 ***
## hospitaldischargeyear2015-16 0.105359
## dialysis1 < 2e-16 ***
## aids1 < 2e-16 ***
## hepaticfailureTRUE 0.167532
## diabetes1 1.07e-07 ***
## immunosuppression1 < 2e-16 ***
## leukemia1 < 2e-16 ***
## lymphoma1 1.38e-13 ***
## metastaticcancer1 0.413868
## thrombolytics1 < 2e-16 ***
## sofa_respiration_baseline2TRUE < 2e-16 ***
## cardiovascular_baseline1 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 647128 on 638756 degrees of freedom
## Residual deviance: 548492 on 638709 degrees of freedom
## AIC: 548588
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$FuzzyLogicADJSepsisPred <- predict(FuzzyLogic_ADJ_Sepsis_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
FuzzyLogicADJSepsis.Pred <- prediction(ssd_incl_te$FuzzyLogicADJSepsisPred, ssd_incl_te$sepsis_outcome)
FuzzyLogicADJSepsis.Perf <- performance(FuzzyLogicADJSepsis.Pred, "tpr", "fpr")
plot(FuzzyLogicADJSepsis.Perf, main = "FuzzyLogic Positive Adjusted Sepsis Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(FuzzyLogicADJSepsis.Pred,"auc")@y.values[[1]],3))) 
performance(FuzzyLogicADJSepsis.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.7706897
##
##
## Slot "alpha.values":
## list()FuzzyLogicADJSepsis.Pred.roc <- roc(sepsis_outcome~FuzzyLogicADJSepsisPred,data=ssd_incl_te)
ci(FuzzyLogicADJSepsis.Pred.roc, conf.level=0.99)## 99% CI: 0.768-0.7734 (DeLong)ggplot(calibration(as.factor(!sepsis_outcome)~FuzzyLogicADJSepsisPred, data = ssd_incl_te))+ggtitle("Calibration of FuzzyLogic Positive Sepsis Prediction")## Warning: Removed 1 rows containing missing values (geom_errorbar).
qplot(FuzzyLogicADJSepsisPred, data = ssd_incl_te)+ggtitle("Histogram of FuzzyLogic Positive Sepsis Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
SIRS1_Crude_Sepsis_tr<-glm(sepsis_outcome ~ (SIRS_total), data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SIRS1_Crude_Sepsis_tr)
#sjt.glm(SIRS1_Crude_Sepsis_tr)
#drop1(SIRS1_Crude_Sepsis_tr,test="Chisq")
summary(SIRS1_Crude_Sepsis_tr)##
## Call:
## glm(formula = sepsis_outcome ~ (SIRS_total), family = "binomial",
## data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.9790 -0.7802 -0.6119 -0.3651 2.3415
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -2.674538 0.008932 -299.4 <2e-16 ***
## SIRS_total 0.547049 0.003252 168.2 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 647128 on 638756 degrees of freedom
## Residual deviance: 616197 on 638755 degrees of freedom
## AIC: 616201
##
## Number of Fisher Scoring iterations: 4ssd_incl_te$SIRS1CrudeSepsisPred <- predict(SIRS1_Crude_Sepsis_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
SIRS1CrudeSepsis.Pred <- prediction(ssd_incl_te$SIRS1CrudeSepsisPred, ssd_incl_te$sepsis_outcome)
SIRS1CrudeSepsis.Perf <- performance(SIRS1CrudeSepsis.Pred, "tpr", "fpr")
plot(SIRS1CrudeSepsis.Perf, main = "SIRS Total Crude Sepsis Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SIRS1CrudeSepsis.Pred,"auc")@y.values[[1]],3))) 
performance(SIRS1CrudeSepsis.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.6502231
##
##
## Slot "alpha.values":
## list()SIRS1CrudeSepsis.Pred.roc <- roc(sepsis_outcome~SIRS1CrudeSepsisPred,data=ssd_incl_te)
ci(SIRS1CrudeSepsis.Pred.roc, conf.level=0.99)## 99% CI: 0.6471-0.6534 (DeLong)ggplot(calibration(as.factor(!sepsis_outcome)~SIRS1CrudeSepsisPred, data = ssd_incl_te))+ggtitle("Calibration of SIRS Total Sepsis Prediction")## Warning: Removed 7 rows containing missing values (geom_errorbar).
qplot(SIRS1CrudeSepsisPred, data = ssd_incl_te)+ggtitle("Histogram of SIRS Total Sepsis Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
SIRS2_Crude_Sepsis_tr<-glm(sepsis_outcome ~ (SIRS_Positive), data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SIRS2_Crude_Sepsis_tr)
#sjt.glm(SIRS2_Crude_Sepsis_tr)
#drop1(SIRS2_Crude_Sepsis_tr,test="Chisq")
summary(SIRS2_Crude_Sepsis_tr)##
## Call:
## glm(formula = sepsis_outcome ~ (SIRS_Positive), family = "binomial",
## data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.7387 -0.7387 -0.7387 -0.4491 2.1653
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -2.243447 0.008668 -258.8 <2e-16 ***
## SIRS_PositiveTRUE 1.084204 0.009299 116.6 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 647128 on 638756 degrees of freedom
## Residual deviance: 630537 on 638755 degrees of freedom
## AIC: 630541
##
## Number of Fisher Scoring iterations: 4ssd_incl_te$SIRS2CrudeSepsisPred <- predict(SIRS2_Crude_Sepsis_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
SIRS2CrudeSepsis.Pred <- prediction(ssd_incl_te$SIRS2CrudeSepsisPred, ssd_incl_te$sepsis_outcome)
SIRS2CrudeSepsis.Perf <- performance(SIRS2CrudeSepsis.Pred, "tpr", "fpr")
plot(SIRS2CrudeSepsis.Perf, main = "SIRS Positive Crude Sepsis Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SIRS2CrudeSepsis.Pred,"auc")@y.values[[1]],3))) 
performance(SIRS2CrudeSepsis.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.5805731
##
##
## Slot "alpha.values":
## list()SIRS2CrudeSepsis.Pred.roc <- roc(sepsis_outcome~SIRS2CrudeSepsisPred,data=ssd_incl_te)
ci(SIRS2CrudeSepsis.Pred.roc, conf.level=0.99)## 99% CI: 0.5785-0.5827 (DeLong)ggplot(calibration(as.factor(!sepsis_outcome)~SIRS2CrudeSepsisPred, data = ssd_incl_te))+ggtitle("Calibration of SIRS Positive Sepsis Prediction")## Warning: Removed 9 rows containing missing values (geom_errorbar).
qplot(SIRS2CrudeSepsisPred, data = ssd_incl_te)+ggtitle("Histogram of SIRS Positive Sepsis Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
qSOFA1_Crude_Sepsis_tr<-glm(sepsis_outcome ~ (qSOFA_total), data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(qSOFA1_Crude_Sepsis_tr)
#sjt.glm(qSOFA1_Crude_Sepsis_tr)
#drop1(qSOFA1_Crude_Sepsis_tr,test="Chisq")
summary(qSOFA1_Crude_Sepsis_tr)##
## Call:
## glm(formula = sepsis_outcome ~ (qSOFA_total), family = "binomial",
## data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.8922 -0.6807 -0.6807 -0.3782 2.3123
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -2.601940 0.009022 -288.4 <2e-16 ***
## qSOFA_total 0.628731 0.004012 156.7 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 647128 on 638756 degrees of freedom
## Residual deviance: 620004 on 638755 degrees of freedom
## AIC: 620008
##
## Number of Fisher Scoring iterations: 4ssd_incl_te$qSOFA1CrudeSepsisPred <- predict(qSOFA1_Crude_Sepsis_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
qSOFA1CrudeSepsis.Pred <- prediction(ssd_incl_te$qSOFA1CrudeSepsisPred, ssd_incl_te$sepsis_outcome)
qSOFA1CrudeSepsis.Perf <- performance(qSOFA1CrudeSepsis.Pred, "tpr", "fpr")
plot(qSOFA1CrudeSepsis.Perf, main = "qSOFA1 Total Crude Sepsis Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(qSOFA1CrudeSepsis.Pred,"auc")@y.values[[1]],3))) 
performance(qSOFA1CrudeSepsis.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.6368558
##
##
## Slot "alpha.values":
## list()qSOFA1CrudeSepsis.Pred.roc <- roc(sepsis_outcome~qSOFA1CrudeSepsisPred,data=ssd_incl_te)
ci(qSOFA1CrudeSepsis.Pred.roc, conf.level=0.99)## 99% CI: 0.6338-0.6399 (DeLong)ggplot(calibration(as.factor(!sepsis_outcome)~qSOFA1CrudeSepsisPred, data = ssd_incl_te))+ggtitle("Calibration of qSOFA Total Sepsis Prediction")## Warning: Removed 7 rows containing missing values (geom_errorbar).
qplot(qSOFA1CrudeSepsisPred, data = ssd_incl_te)+ggtitle("Histogram of qSOFA Total Sepsis Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
qSOFA2_Crude_Sepsis_tr<-glm(sepsis_outcome ~ (qSOFA_Positive), data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(qSOFA2_Crude_Sepsis_tr)
#sjt.glm(qSOFA2_Crude_Sepsis_tr)
#drop1(qSOFA2_Crude_Sepsis_tr,test="Chisq")
summary(qSOFA2_Crude_Sepsis_tr)##
## Call:
## glm(formula = sepsis_outcome ~ (qSOFA_Positive), family = "binomial",
## data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.7565 -0.7565 -0.7565 -0.4915 2.0849
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -2.052644 0.006875 -298.6 <2e-16 ***
## qSOFA_PositiveTRUE 0.947849 0.007729 122.6 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 647128 on 638756 degrees of freedom
## Residual deviance: 630027 on 638755 degrees of freedom
## AIC: 630031
##
## Number of Fisher Scoring iterations: 4ssd_incl_te$qSOFA2CrudeSepsisPred <- predict(qSOFA2_Crude_Sepsis_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
qSOFA2CrudeSepsis.Pred <- prediction(ssd_incl_te$qSOFA2CrudeSepsisPred, ssd_incl_te$sepsis_outcome)
qSOFA2CrudeSepsis.Perf <- performance(qSOFA2CrudeSepsis.Pred, "tpr", "fpr")
plot(qSOFA2CrudeSepsis.Perf, main = "qSOFA Positive Crude Sepsis Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(qSOFA2CrudeSepsis.Pred,"auc")@y.values[[1]],3))) 
performance(qSOFA2CrudeSepsis.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.5928223
##
##
## Slot "alpha.values":
## list()qSOFA2CrudeSepsis.Pred.roc <- roc(sepsis_outcome~qSOFA2CrudeSepsisPred,data=ssd_incl_te)
ci(qSOFA2CrudeSepsis.Pred.roc, conf.level=0.99)## 99% CI: 0.5903-0.5953 (DeLong)ggplot(calibration(as.factor(!sepsis_outcome)~qSOFA2CrudeSepsisPred, data = ssd_incl_te))+ggtitle("Calibration of qSOFA Positive Sepsis Prediction")## Warning: Removed 9 rows containing missing values (geom_errorbar).
qplot(qSOFA2CrudeSepsisPred, data = ssd_incl_te)+ggtitle("Histogram of qSOFA Positive Sepsis Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
SOFA1_Crude_Sepsis_tr<-glm(sepsis_outcome ~ as.factor(SOFA_Change), data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SOFA1_Crude_Sepsis_tr)
#sjt.glm(SOFA1_Crude_Sepsis_tr)
#drop1(SOFA1_Crude_Sepsis_tr,test="Chisq")
summary(SOFA1_Crude_Sepsis_tr)##
## Call:
## glm(formula = sepsis_outcome ~ as.factor(SOFA_Change), family = "binomial",
## data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.4096 -0.7412 -0.5635 -0.3790 2.3105
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -2.59739 0.01702 -152.61 <2e-16 ***
## as.factor(SOFA_Change) 1 0.40363 0.01913 21.10 <2e-16 ***
## as.factor(SOFA_Change) 2 0.83756 0.01933 43.32 <2e-16 ***
## as.factor(SOFA_Change) 3 1.25489 0.01909 65.75 <2e-16 ***
## as.factor(SOFA_Change) 4 1.44584 0.01915 75.50 <2e-16 ***
## as.factor(SOFA_Change) 5 1.59643 0.01951 81.82 <2e-16 ***
## as.factor(SOFA_Change) 6 1.84006 0.02015 91.32 <2e-16 ***
## as.factor(SOFA_Change) 7 1.91239 0.02084 91.78 <2e-16 ***
## as.factor(SOFA_Change) 8 2.01564 0.02226 90.55 <2e-16 ***
## as.factor(SOFA_Change) 9 2.12645 0.02408 88.30 <2e-16 ***
## as.factor(SOFA_Change)10 2.20521 0.02644 83.40 <2e-16 ***
## as.factor(SOFA_Change)11 2.25783 0.02949 76.57 <2e-16 ***
## as.factor(SOFA_Change)12 2.38680 0.03413 69.94 <2e-16 ***
## as.factor(SOFA_Change)13 2.50214 0.03973 62.97 <2e-16 ***
## as.factor(SOFA_Change)14 2.55797 0.04808 53.20 <2e-16 ***
## as.factor(SOFA_Change)15 2.74004 0.05891 46.51 <2e-16 ***
## as.factor(SOFA_Change)16 2.78495 0.07437 37.45 <2e-16 ***
## as.factor(SOFA_Change)17 2.82860 0.10323 27.40 <2e-16 ***
## as.factor(SOFA_Change)[18,23] 3.12842 0.10532 29.70 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 647128 on 638756 degrees of freedom
## Residual deviance: 604543 on 638738 degrees of freedom
## AIC: 604581
##
## Number of Fisher Scoring iterations: 5ssd_incl_te$SOFA1CrudeSepsisPred <- predict(SOFA1_Crude_Sepsis_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
SOFA1CrudeSepsis.Pred <- prediction(ssd_incl_te$SOFA1CrudeSepsisPred, ssd_incl_te$sepsis_outcome)
SOFA1CrudeSepsis.Perf <- performance(SOFA1CrudeSepsis.Pred, "tpr", "fpr")
plot(SOFA1CrudeSepsis.Perf, main = "SOFA Continuous Crude Sepsis Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SOFA1CrudeSepsis.Pred,"auc")@y.values[[1]],3))) 
performance(SOFA1CrudeSepsis.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.6796153
##
##
## Slot "alpha.values":
## list()SOFA1CrudeSepsis.Pred.roc <- roc(sepsis_outcome~SOFA1CrudeSepsisPred,data=ssd_incl_te)
ci(SOFA1CrudeSepsis.Pred.roc, conf.level=0.99)## 99% CI: 0.6764-0.6828 (DeLong)ggplot(calibration(as.factor(!sepsis_outcome)~SOFA1CrudeSepsisPred, data = ssd_incl_te))+ggtitle("Calibration of SOFA Total Sepsis Prediction")## Warning: Removed 4 rows containing missing values (geom_errorbar).
qplot(SOFA1CrudeSepsisPred, data = ssd_incl_te)+ggtitle("Histogram of SOFA Total Sepsis Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
SOFA2_Crude_Sepsis_tr<-glm(sepsis_outcome ~ as.factor(SOFA_Positive), data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SOFA2_Crude_Sepsis_tr)
#sjt.glm(SOFA2_Crude_Sepsis_tr)
#drop1(SOFA2_Crude_Sepsis_tr,test="Chisq")
summary(SOFA2_Crude_Sepsis_tr)##
## Call:
## glm(formula = sepsis_outcome ~ as.factor(SOFA_Positive), family = "binomial",
## data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.7680 -0.7680 -0.7680 -0.4393 2.1846
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -2.289758 0.007755 -295.3 <2e-16 ***
## as.factor(SOFA_Positive)TRUE 1.219750 0.008491 143.7 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 647128 on 638756 degrees of freedom
## Residual deviance: 621940 on 638755 degrees of freedom
## AIC: 621944
##
## Number of Fisher Scoring iterations: 4ssd_incl_te$SOFA2CrudeSepsisPred <- predict(SOFA2_Crude_Sepsis_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
SOFA2CrudeSepsis.Pred <- prediction(ssd_incl_te$SOFA2CrudeSepsisPred, ssd_incl_te$sepsis_outcome)
SOFA2CrudeSepsis.Perf <- performance(SOFA2CrudeSepsis.Pred, "tpr", "fpr")
plot(SOFA2CrudeSepsis.Perf, main = "SOFA Positive Crude Sepsis Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SOFA2CrudeSepsis.Pred,"auc")@y.values[[1]],3))) 
performance(SOFA2CrudeSepsis.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.6087716
##
##
## Slot "alpha.values":
## list()SOFA2CrudeSepsis.Pred.roc <- roc(sepsis_outcome~SOFA2CrudeSepsisPred,data=ssd_incl_te)
ci(SOFA2CrudeSepsis.Pred.roc, conf.level=0.99)## 99% CI: 0.6065-0.6111 (DeLong)ggplot(calibration(as.factor(!sepsis_outcome)~SOFA2CrudeSepsisPred, data = ssd_incl_te))+ggtitle("Calibration of SOFA Positive Sepsis Prediction")## Warning: Removed 9 rows containing missing values (geom_errorbar).
qplot(SOFA2CrudeSepsisPred, data = ssd_incl_te)+ggtitle("Histogram of SOFA Positive Sepsis Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
SOFA3_Crude_Sepsis_tr<-glm(sepsis_outcome ~ as.factor(SOFA_Positive2), data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(SOFA3_Crude_Sepsis_tr)
#sjt.glm(SOFA3_Crude_Sepsis_tr)
#drop1(SOFA3_Crude_Sepsis_tr,test="Chisq")
summary(SOFA3_Crude_Sepsis_tr)##
## Call:
## glm(formula = sepsis_outcome ~ as.factor(SOFA_Positive2), family = "binomial",
## data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.7663 -0.7663 -0.7663 -0.4193 2.2250
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -2.387468 0.008324 -286.8 <2e-16 ***
## as.factor(SOFA_Positive2)TRUE 1.312243 0.008998 145.8 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 647128 on 638756 degrees of freedom
## Residual deviance: 620236 on 638755 degrees of freedom
## AIC: 620240
##
## Number of Fisher Scoring iterations: 5ssd_incl_te$SOFA3CrudeSepsisPred <- predict(SOFA3_Crude_Sepsis_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
SOFA3CrudeSepsis.Pred <- prediction(ssd_incl_te$SOFA3CrudeSepsisPred, ssd_incl_te$sepsis_outcome)
SOFA3CrudeSepsis.Perf <- performance(SOFA3CrudeSepsis.Pred, "tpr", "fpr")
plot(SOFA3CrudeSepsis.Perf, main = "SOFA Positive w/o Baseline
Crude Sepsis Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(SOFA3CrudeSepsis.Pred,"auc")@y.values[[1]],3))) 
performance(SOFA3CrudeSepsis.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.6088949
##
##
## Slot "alpha.values":
## list()SOFA3CrudeSepsis.Pred.roc <- roc(sepsis_outcome~SOFA3CrudeSepsisPred,data=ssd_incl_te)
ci(SOFA3CrudeSepsis.Pred.roc, conf.level=0.99)## 99% CI: 0.6067-0.6111 (DeLong)ggplot(calibration(as.factor(!sepsis_outcome)~SOFA3CrudeSepsisPred, data = ssd_incl_te))+ggtitle("Calibration of SOFA Positive w/o Baseline Sepsis Prediction")## Warning: Removed 9 rows containing missing values (geom_errorbar).
qplot(SOFA3CrudeSepsisPred, data = ssd_incl_te)+ggtitle("Histogram of SOFA Positive w/o Baseline Sepsis Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
FuzzyLogic_Crude_Sepsis_tr<-glm(sepsis_outcome ~ (SepsisFuzzyLogicPositive), data=ssd_incl_tr,family="binomial",na.action = na.omit)
#sjp.glm(FuzzyLogic_ADJ_Sepsis_tr)
#sjt.glm(FuzzyLogic_ADJ_Sepsis_tr)
#drop1(FuzzyLogic_ADJ_Sepsis_tr,test="Chisq")
summary(FuzzyLogic_ADJ_Sepsis_tr)##
## Call:
## glm(formula = sepsis_outcome ~ (SepsisFuzzyLogicPositive) + age_Ranges +
## gender2 + ethnicity2 + BMI_Ranges + icu_admit_source2 + hospital_teaching_status +
## hospital_size + physicianSpeciality2 + hospitaldischargeyear +
## dialysis + aids + hepaticfailure + diabetes + immunosuppression +
## leukemia + lymphoma + metastaticcancer + thrombolytics +
## sofa_respiration_baseline2 + cardiovascular_baseline, family = "binomial",
## data = ssd_incl_tr, na.action = na.omit)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.0787 -0.7206 -0.4234 -0.1814 3.6169
##
## Coefficients:
## Estimate Std. Error z value
## (Intercept) -2.124152 0.033816 -62.815
## SepsisFuzzyLogicPositiveTRUE 1.494644 0.007929 188.497
## age_Ranges(25,35] 0.200047 0.027507 7.272
## age_Ranges(35,45] 0.380838 0.025582 14.887
## age_Ranges(45,55] 0.539099 0.023648 22.797
## age_Ranges(55,65] 0.710904 0.023120 30.748
## age_Ranges(65,75] 0.744332 0.023110 32.209
## age_Ranges(75,85] 0.822203 0.023233 35.390
## age_Ranges(85,100] 0.957012 0.024461 39.125
## gender2Female 0.036346 0.006828 5.323
## gender2Other/Unknown -1.078963 0.267177 -4.038
## ethnicity2African American -0.029079 0.011073 -2.626
## ethnicity2Hispanic 0.399012 0.015308 26.065
## ethnicity2Asian 0.110971 0.029812 3.722
## ethnicity2Native American 0.266320 0.037867 7.033
## ethnicity2Other/Unknown 0.046935 0.014927 3.144
## BMI_Ranges(18.5,25] -0.220140 0.015229 -14.455
## BMI_Ranges(25,35] -0.286701 0.014915 -19.222
## BMI_Ranges(35,200] -0.114540 0.016172 -7.083
## BMI_RangesOther/Unknown -0.465796 0.023828 -19.548
## icu_admit_source2OR/Proc Area -1.996615 0.014573 -137.012
## icu_admit_source2Direct Admit -0.459874 0.012939 -35.543
## icu_admit_source2Emergency Department -0.280337 0.008454 -33.161
## icu_admit_source2Other -0.107824 0.033765 -3.193
## icu_admit_source2Step-Down Unit 0.055622 0.021391 2.600
## hospital_teaching_statusf -0.240214 0.024886 -9.652
## hospital_teaching_statust -0.207117 0.025137 -8.240
## hospital_size<100 0.621431 0.023826 26.082
## hospital_size100-249 0.311101 0.019367 16.063
## hospital_size250-500 0.262875 0.019696 13.346
## hospital_size>500 0.108788 0.018436 5.901
## physicianSpeciality2Speciality-Other -0.501852 0.007684 -65.313
## hospitaldischargeyear2011 0.092410 0.013172 7.016
## hospitaldischargeyear2012 -0.039503 0.012781 -3.091
## hospitaldischargeyear2013 -0.038688 0.012491 -3.097
## hospitaldischargeyear2014 -0.059266 0.012397 -4.781
## hospitaldischargeyear2015-16 -0.019868 0.012269 -1.619
## dialysis1 0.270859 0.017788 15.227
## aids1 1.331422 0.089546 14.869
## hepaticfailureTRUE -0.029653 0.021485 -1.380
## diabetes1 0.044792 0.008428 5.315
## immunosuppression1 0.526333 0.020537 25.628
## leukemia1 0.399091 0.034129 11.694
## lymphoma1 0.345324 0.046675 7.399
## metastaticcancer1 0.019801 0.024233 0.817
## thrombolytics1 -2.110673 0.060512 -34.880
## sofa_respiration_baseline2TRUE 0.392935 0.007544 52.086
## cardiovascular_baseline1 -0.072916 0.008255 -8.833
## Pr(>|z|)
## (Intercept) < 2e-16 ***
## SepsisFuzzyLogicPositiveTRUE < 2e-16 ***
## age_Ranges(25,35] 3.53e-13 ***
## age_Ranges(35,45] < 2e-16 ***
## age_Ranges(45,55] < 2e-16 ***
## age_Ranges(55,65] < 2e-16 ***
## age_Ranges(65,75] < 2e-16 ***
## age_Ranges(75,85] < 2e-16 ***
## age_Ranges(85,100] < 2e-16 ***
## gender2Female 1.02e-07 ***
## gender2Other/Unknown 5.38e-05 ***
## ethnicity2African American 0.008635 **
## ethnicity2Hispanic < 2e-16 ***
## ethnicity2Asian 0.000197 ***
## ethnicity2Native American 2.02e-12 ***
## ethnicity2Other/Unknown 0.001665 **
## BMI_Ranges(18.5,25] < 2e-16 ***
## BMI_Ranges(25,35] < 2e-16 ***
## BMI_Ranges(35,200] 1.41e-12 ***
## BMI_RangesOther/Unknown < 2e-16 ***
## icu_admit_source2OR/Proc Area < 2e-16 ***
## icu_admit_source2Direct Admit < 2e-16 ***
## icu_admit_source2Emergency Department < 2e-16 ***
## icu_admit_source2Other 0.001406 **
## icu_admit_source2Step-Down Unit 0.009314 **
## hospital_teaching_statusf < 2e-16 ***
## hospital_teaching_statust < 2e-16 ***
## hospital_size<100 < 2e-16 ***
## hospital_size100-249 < 2e-16 ***
## hospital_size250-500 < 2e-16 ***
## hospital_size>500 3.61e-09 ***
## physicianSpeciality2Speciality-Other < 2e-16 ***
## hospitaldischargeyear2011 2.29e-12 ***
## hospitaldischargeyear2012 0.001996 **
## hospitaldischargeyear2013 0.001952 **
## hospitaldischargeyear2014 1.75e-06 ***
## hospitaldischargeyear2015-16 0.105359
## dialysis1 < 2e-16 ***
## aids1 < 2e-16 ***
## hepaticfailureTRUE 0.167532
## diabetes1 1.07e-07 ***
## immunosuppression1 < 2e-16 ***
## leukemia1 < 2e-16 ***
## lymphoma1 1.38e-13 ***
## metastaticcancer1 0.413868
## thrombolytics1 < 2e-16 ***
## sofa_respiration_baseline2TRUE < 2e-16 ***
## cardiovascular_baseline1 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 647128 on 638756 degrees of freedom
## Residual deviance: 548492 on 638709 degrees of freedom
## AIC: 548588
##
## Number of Fisher Scoring iterations: 6ssd_incl_te$FuzzyLogicCrudeSepsisPred <- predict(FuzzyLogic_Crude_Sepsis_tr,newdata=ssd_incl_te,na.action=na.pass,type="response")
library(sjPlot)
library(ROCR)
FuzzyLogicCrudeSepsis.Pred <- prediction(ssd_incl_te$FuzzyLogicCrudeSepsisPred, ssd_incl_te$sepsis_outcome)
FuzzyLogicCrudeSepsis.Perf <- performance(FuzzyLogicCrudeSepsis.Pred, "tpr", "fpr")
plot(FuzzyLogicCrudeSepsis.Perf, main = "FuzzyLogic Positive Crude Sepsis Prediction Test Model")
text(0.7,0.2,label=paste0("AUC:",round(performance(FuzzyLogicCrudeSepsis.Pred,"auc")@y.values[[1]],3))) 
performance(FuzzyLogicCrudeSepsis.Pred, "auc")## An object of class "performance"
## Slot "x.name":
## [1] "None"
##
## Slot "y.name":
## [1] "Area under the ROC curve"
##
## Slot "alpha.name":
## [1] "none"
##
## Slot "x.values":
## list()
##
## Slot "y.values":
## [[1]]
## [1] 0.6665731
##
##
## Slot "alpha.values":
## list()FuzzyLogicCrudeSepsis.Pred.roc <- roc(sepsis_outcome~FuzzyLogicCrudeSepsisPred,data=ssd_incl_te)
ci(FuzzyLogicCrudeSepsis.Pred.roc, conf.level=0.99)## 99% CI: 0.6641-0.6691 (DeLong)ggplot(calibration(as.factor(!sepsis_outcome)~FuzzyLogicCrudeSepsisPred, data = ssd_incl_te))+ggtitle("Calibration of FuzzyLogic Positive Sepsis Prediction")## Warning: Removed 9 rows containing missing values (geom_errorbar).
qplot(FuzzyLogicCrudeSepsisPred, data = ssd_incl_te)+ggtitle("Histogram of FuzzyLogic Positive Sepsis Predictions")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
23 Setting up variables to analyze interactions
ssd_incl_te <- ssd_incl_te %>% mutate(SIRS2TruthSepsis=interaction (SIRS_Positive,sepsis_outcome))
ssd_incl_te <- ssd_incl_te %>% mutate(qSOFA2TruthSepsis=interaction (qSOFA_Positive,sepsis_outcome))
ssd_incl_te <- ssd_incl_te %>% mutate(SOFA2TruthSepsis=interaction (SOFA_Positive,sepsis_outcome))
ssd_incl_te <- ssd_incl_te %>% mutate(FuzzyLogicTruthSepsis=interaction (SepsisFuzzyLogicPositive,sepsis_outcome))vars5 <- c("age_Ranges", "gender2", "ethnicity2", "BMI_Ranges", "physicianSpeciality2", "icu_admit_source2", "icu_disch_location2", "hospitaldischargeyear", "dischargelocation", "dialysis", "aids", "hepaticfailure", "diabetes", "immunosuppression" , "leukemia", "lymphoma", "metastaticcancer", "thrombolytics", "sofa_respiration_baseline2", "sofa_liver_baseline2", "sofa_renal_baseline2", "cardiovascular_baseline", "group" )
library(dplyr); library(Hmisc); library(ggplot2); #library(sjPlot)
if(!("tableone" %in% rownames(installed.packages()))) {
install.packages("tableone")
}
library(dplyr); library(Hmisc); library(ggplot2); #library(sjPlot)
library(tableone)
CreateTableOne(data=ssd_incl_te ,vars=vars5,strata="SIRS2TruthSepsis",test=FALSE, includeNA=TRUE
) %>% print(nonnormal= c("sofa_respiration_baseline", "sofa_liver_baseline", "sofa_renal_baseline"),minMax=TRUE,
printToggle = FALSE,
showAllLevels = TRUE,
cramVars = "kon"
) %>%
{data.frame(
variable_name = gsub(" ", " ", rownames(.), fixed = TRUE), .,
row.names = NULL,
check.names = FALSE,
stringsAsFactors = FALSE)} %>%
knitr::kable(caption="SIRS positive negative sepsis outcome")| variable_name | level | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE |
|---|---|---|---|---|---|
| n | 59019 | 158477 | 6200 | 50056 | |
| age_Ranges (%) | (0,25] | 1497 ( 2.5) | 6467 ( 4.1) | 50 ( 0.8) | 1037 ( 2.1) |
| (25,35] | 2487 ( 4.2) | 9392 ( 5.9) | 150 ( 2.4) | 2031 ( 4.1) | |
| (35,45] | 3958 ( 6.7) | 13094 ( 8.3) | 246 ( 4.0) | 3030 ( 6.1) | |
| (45,55] | 8810 ( 14.9) | 24376 (15.4) | 803 (13.0) | 6540 (13.1) | |
| (55,65] | 12717 ( 21.5) | 32813 (20.7) | 1288 (20.8) | 10286 (20.5) | |
| (65,75] | 13662 ( 23.1) | 33702 (21.3) | 1517 (24.5) | 11725 (23.4) | |
| (75,85] | 11188 ( 19.0) | 26913 (17.0) | 1418 (22.9) | 10103 (20.2) | |
| (85,100] | 4700 ( 8.0) | 11720 ( 7.4) | 728 (11.7) | 5304 (10.6) | |
| gender2 (%) | Male | 33335 ( 56.5) | 85328 (53.8) | 3126 (50.4) | 25113 (50.2) |
| Female | 25670 ( 43.5) | 73095 (46.1) | 3074 (49.6) | 24931 (49.8) | |
| Other/Unknown | 14 ( 0.0) | 54 ( 0.0) | 0 ( 0.0) | 12 ( 0.0) | |
| ethnicity2 (%) | Caucasian | 44895 ( 76.1) | 121150 (76.4) | 4622 (74.5) | 38021 (76.0) |
| African American | 6653 ( 11.3) | 18953 (12.0) | 674 (10.9) | 5449 (10.9) | |
| Hispanic | 2668 ( 4.5) | 6357 ( 4.0) | 410 ( 6.6) | 2850 ( 5.7) | |
| Asian | 761 ( 1.3) | 2024 ( 1.3) | 84 ( 1.4) | 664 ( 1.3) | |
| Native American | 407 ( 0.7) | 1151 ( 0.7) | 53 ( 0.9) | 401 ( 0.8) | |
| Other/Unknown | 3635 ( 6.2) | 8842 ( 5.6) | 357 ( 5.8) | 2671 ( 5.3) | |
| BMI_Ranges (%) | (0,18.5] | 2204 ( 3.7) | 7542 ( 4.8) | 331 ( 5.3) | 3371 ( 6.7) |
| (18.5,25] | 15631 ( 26.5) | 44539 (28.1) | 1693 (27.3) | 15012 (30.0) | |
| (25,35] | 29041 ( 49.2) | 72828 (46.0) | 2588 (41.7) | 20755 (41.5) | |
| (35,200] | 9515 ( 16.1) | 28123 (17.7) | 1352 (21.8) | 9467 (18.9) | |
| Other/Unknown | 2628 ( 4.5) | 5445 ( 3.4) | 236 ( 3.8) | 1451 ( 2.9) | |
| physicianSpeciality2 (%) | Critical Care | 11115 ( 18.8) | 47303 (29.8) | 2028 (32.7) | 19849 (39.7) |
| Speciality-Other | 47904 ( 81.2) | 111174 (70.2) | 4172 (67.3) | 30207 (60.3) | |
| icu_admit_source2 (%) | Floor | 7769 ( 13.2) | 24660 (15.6) | 1460 (23.5) | 12545 (25.1) |
| OR/Proc Area | 11280 ( 19.1) | 38657 (24.4) | 279 ( 4.5) | 2715 ( 5.4) | |
| Direct Admit | 7535 ( 12.8) | 16746 (10.6) | 483 ( 7.8) | 4707 ( 9.4) | |
| Emergency Department | 31279 ( 53.0) | 73813 (46.6) | 3755 (60.6) | 27827 (55.6) | |
| Other | 361 ( 0.6) | 1361 ( 0.9) | 55 ( 0.9) | 583 ( 1.2) | |
| Step-Down Unit | 795 ( 1.3) | 3240 ( 2.0) | 168 ( 2.7) | 1679 ( 3.4) | |
| icu_disch_location2 (%) | Floor | 41911 ( 71.0) | 117529 (74.2) | 4876 (78.6) | 35103 (70.1) |
| Death | 775 ( 1.3) | 10088 ( 6.4) | 309 ( 5.0) | 7183 (14.3) | |
| Home | 11221 ( 19.0) | 13662 ( 8.6) | 330 ( 5.3) | 1470 ( 2.9) | |
| SNF/Rehab | 653 ( 1.1) | 1995 ( 1.3) | 195 ( 3.1) | 1415 ( 2.8) | |
| Other | 1545 ( 2.6) | 5027 ( 3.2) | 197 ( 3.2) | 2036 ( 4.1) | |
| Other Hospital | 1223 ( 2.1) | 3434 ( 2.2) | 144 ( 2.3) | 1355 ( 2.7) | |
| Step-Down Unit | 1691 ( 2.9) | 6742 ( 4.3) | 149 ( 2.4) | 1494 ( 3.0) | |
| hospitaldischargeyear (%) | -2010 | 8182 ( 13.9) | 18265 (11.5) | 797 (12.9) | 6104 (12.2) |
| 2011 | 8248 ( 14.0) | 20448 (12.9) | 938 (15.1) | 7180 (14.3) | |
| 2012 | 9659 ( 16.4) | 26048 (16.4) | 950 (15.3) | 8153 (16.3) | |
| 2013 | 10589 ( 17.9) | 29524 (18.6) | 1097 (17.7) | 9052 (18.1) | |
| 2014 | 11459 ( 19.4) | 31504 (19.9) | 1231 (19.9) | 9357 (18.7) | |
| 2015-16 | 10882 ( 18.4) | 32688 (20.6) | 1187 (19.1) | 10210 (20.4) | |
| dischargelocation (mean (sd)) | 5.23 (1.68) | 5.30 (1.86) | 5.01 (1.73) | 5.43 (2.05) | |
| dialysis (%) | 0 | 57032 ( 96.6) | 153514 (96.9) | 5861 (94.5) | 48087 (96.1) |
| 1 | 1987 ( 3.4) | 4963 ( 3.1) | 339 ( 5.5) | 1969 ( 3.9) | |
| aids (%) | 0 | 58999 (100.0) | 158392 (99.9) | 6187 (99.8) | 49911 (99.7) |
| 1 | 20 ( 0.0) | 85 ( 0.1) | 13 ( 0.2) | 145 ( 0.3) | |
| hepaticfailure (%) | FALSE | 58024 ( 98.3) | 155221 (97.9) | 6031 (97.3) | 48795 (97.5) |
| TRUE | 995 ( 1.7) | 3256 ( 2.1) | 169 ( 2.7) | 1261 ( 2.5) | |
| diabetes (%) | 0 | 46071 ( 78.1) | 123897 (78.2) | 4557 (73.5) | 39395 (78.7) |
| 1 | 12948 ( 21.9) | 34580 (21.8) | 1643 (26.5) | 10661 (21.3) | |
| immunosuppression (%) | 0 | 58280 ( 98.7) | 155067 (97.8) | 6026 (97.2) | 48013 (95.9) |
| 1 | 739 ( 1.3) | 3410 ( 2.2) | 174 ( 2.8) | 2043 ( 4.1) | |
| leukemia (%) | 0 | 58808 ( 99.6) | 157498 (99.4) | 6156 (99.3) | 49352 (98.6) |
| 1 | 211 ( 0.4) | 979 ( 0.6) | 44 ( 0.7) | 704 ( 1.4) | |
| lymphoma (%) | 0 | 58868 ( 99.7) | 157942 (99.7) | 6177 (99.6) | 49735 (99.4) |
| 1 | 151 ( 0.3) | 535 ( 0.3) | 23 ( 0.4) | 321 ( 0.6) | |
| metastaticcancer (%) | 0 | 58219 ( 98.6) | 155333 (98.0) | 6102 (98.4) | 48792 (97.5) |
| 1 | 800 ( 1.4) | 3144 ( 2.0) | 98 ( 1.6) | 1264 ( 2.5) | |
| thrombolytics (%) | 0 | 57043 ( 96.7) | 155581 (98.2) | 6193 (99.9) | 49967 (99.8) |
| 1 | 1976 ( 3.3) | 2896 ( 1.8) | 7 ( 0.1) | 89 ( 0.2) | |
| sofa_respiration_baseline2 (%) | FALSE | 48496 ( 82.2) | 122329 (77.2) | 3953 (63.8) | 33230 (66.4) |
| TRUE | 10523 ( 17.8) | 36148 (22.8) | 2247 (36.2) | 16826 (33.6) | |
| sofa_liver_baseline2 (%) | FALSE | 58024 ( 98.3) | 155221 (97.9) | 6031 (97.3) | 48795 (97.5) |
| TRUE | 995 ( 1.7) | 3256 ( 2.1) | 169 ( 2.7) | 1261 ( 2.5) | |
| sofa_renal_baseline2 (%) | FALSE | 57032 ( 96.6) | 153514 (96.9) | 5861 (94.5) | 48087 (96.1) |
| TRUE | 1987 ( 3.4) | 4963 ( 3.1) | 339 ( 5.5) | 1969 ( 3.9) | |
| cardiovascular_baseline (%) | 0 | 44589 ( 75.6) | 124723 (78.7) | 4265 (68.8) | 38284 (76.5) |
| 1 | 14430 ( 24.4) | 33754 (21.3) | 1935 (31.2) | 11772 (23.5) | |
| group (%) | Cardiovascular | 26820 ( 45.4) | 55465 (35.0) | 830 (13.4) | 5248 (10.5) |
| Gastrointestinal | 5558 ( 9.4) | 19470 (12.3) | 348 ( 5.6) | 3168 ( 6.3) | |
| Gynaecological | 103 ( 0.2) | 579 ( 0.4) | 2 ( 0.0) | 31 ( 0.1) | |
| Hematological | 396 ( 0.7) | 1383 ( 0.9) | 33 ( 0.5) | 274 ( 0.5) | |
| Metabolic | 5526 ( 9.4) | 15086 ( 9.5) | 297 ( 4.8) | 1552 ( 3.1) | |
| Muscoskeletal/Skin disease | 649 ( 1.1) | 2130 ( 1.3) | 77 ( 1.2) | 602 ( 1.2) | |
| Neurological | 10203 ( 17.3) | 23845 (15.0) | 457 ( 7.4) | 2332 ( 4.7) | |
| Renal/Genitourinary | 1340 ( 2.3) | 3749 ( 2.4) | 231 ( 3.7) | 1256 ( 2.5) | |
| Respiratory | 4715 ( 8.0) | 22238 (14.0) | 1629 (26.3) | 12276 (24.5) | |
| Sepsis | 360 ( 0.6) | 3890 ( 2.5) | 2249 (36.3) | 22838 (45.6) | |
| Trauma | 2883 ( 4.9) | 8928 ( 5.6) | 28 ( 0.5) | 286 ( 0.6) | |
| Undefined | 466 ( 0.8) | 1714 ( 1.1) | 19 ( 0.3) | 193 ( 0.4) |
library(tidyr)
ssd_incl_te%>%group_by(hospitaldischargeyear,SIRS2TruthSepsis) %>%summarise(n=n())%>%spread(SIRS2TruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| hospitaldischargeyear | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| -2010 | 8182 | 18265 | 797 | 6104 | 0.8845095 | 0.3093735 |
| 2011 | 8248 | 20448 | 938 | 7180 | 0.8844543 | 0.2874268 |
| 2012 | 9659 | 26048 | 950 | 8153 | 0.8956388 | 0.2705072 |
| 2013 | 10589 | 29524 | 1097 | 9052 | 0.8919105 | 0.2639793 |
| 2014 | 11459 | 31504 | 1231 | 9357 | 0.8837363 | 0.2667179 |
| 2015-16 | 10882 | 32688 | 1187 | 10210 | 0.8958498 | 0.2497590 |
ssd_incl_te%>%group_by(hospitaldischargeyear,SIRS2TruthSepsis) %>%summarise(n=n())%>%spread(SIRS2TruthSepsis,n)%>%head()## # A tibble: 6 x 5
## # Groups: hospitaldischargeyear [6]
## hospitaldischargeyear FALSE.FALSE TRUE.FALSE FALSE.TRUE TRUE.TRUE
## <chr> <int> <int> <int> <int>
## 1 -2010 8182 18265 797 6104
## 2 2011 8248 20448 938 7180
## 3 2012 9659 26048 950 8153
## 4 2013 10589 29524 1097 9052
## 5 2014 11459 31504 1231 9357
## 6 2015-16 10882 32688 1187 10210ssd_incl_te%>%group_by(age_Ranges,SIRS2TruthSepsis) %>%summarise(n=n())%>%spread(SIRS2TruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| age_Ranges | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| (0,25] | 1497 | 6467 | 50 | 1037 | 0.9540018 | 0.1879709 |
| (25,35] | 2487 | 9392 | 150 | 2031 | 0.9312242 | 0.2093611 |
| (35,45] | 3958 | 13094 | 246 | 3030 | 0.9249084 | 0.2321135 |
| (45,55] | 8810 | 24376 | 803 | 6540 | 0.8906442 | 0.2654734 |
| (55,65] | 12717 | 32813 | 1288 | 10286 | 0.8887161 | 0.2793103 |
| (65,75] | 13662 | 33702 | 1517 | 11725 | 0.8854403 | 0.2884469 |
| (75,85] | 11188 | 26913 | 1418 | 10103 | 0.8769204 | 0.2936406 |
| (85,100] | 4700 | 11720 | 728 | 5304 | 0.8793103 | 0.2862363 |
ssd_incl_te%>%group_by(BMI_Ranges,SIRS2TruthSepsis) %>%summarise(n=n())%>%spread(SIRS2TruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| BMI_Ranges | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| (0,18.5] | 2204 | 7542 | 331 | 3371 | 0.9105889 | 0.2261441 |
| (18.5,25] | 15631 | 44539 | 1693 | 15012 | 0.8986531 | 0.2597806 |
| (25,35] | 29041 | 72828 | 2588 | 20755 | 0.8891316 | 0.2850818 |
| (35,200] | 9515 | 28123 | 1352 | 9467 | 0.8750347 | 0.2528030 |
| Other/Unknown | 2628 | 5445 | 236 | 1451 | 0.8601067 | 0.3255295 |
ssd_incl_te%>%group_by(icu_admit_source2,SIRS2TruthSepsis) %>%summarise(n=n())%>%spread(SIRS2TruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| icu_admit_source2 | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| Floor | 7769 | 24660 | 1460 | 12545 | 0.8957515 | 0.2395695 |
| OR/Proc Area | 11280 | 38657 | 279 | 2715 | 0.9068136 | 0.2258846 |
| Direct Admit | 7535 | 16746 | 483 | 4707 | 0.9069364 | 0.3103249 |
| Emergency Department | 31279 | 73813 | 3755 | 27827 | 0.8811032 | 0.2976345 |
| Other | 361 | 1361 | 55 | 583 | 0.9137931 | 0.2096400 |
| Step-Down Unit | 795 | 3240 | 168 | 1679 | 0.9090417 | 0.1970260 |
ssd_incl_te%>%group_by(ethnicity2,SIRS2TruthSepsis) %>%summarise(n=n())%>%spread(SIRS2TruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| ethnicity2 | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| Caucasian | 44895 | 121150 | 4622 | 38021 | 0.8916118 | 0.2703785 |
| African American | 6653 | 18953 | 674 | 5449 | 0.8899232 | 0.2598219 |
| Hispanic | 2668 | 6357 | 410 | 2850 | 0.8742331 | 0.2956233 |
| Asian | 761 | 2024 | 84 | 664 | 0.8877005 | 0.2732496 |
| Native American | 407 | 1151 | 53 | 401 | 0.8832599 | 0.2612323 |
| Other/Unknown | 3635 | 8842 | 357 | 2671 | 0.8821004 | 0.2913361 |
ssd_incl_te%>%group_by(physicianSpeciality2,SIRS2TruthSepsis) %>%summarise(n=n())%>%spread(SIRS2TruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| physicianSpeciality2 | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| Critical Care | 11115 | 47303 | 2028 | 19849 | 0.9072999 | 0.1902667 |
| Speciality-Other | 47904 | 111174 | 4172 | 30207 | 0.8786468 | 0.3011353 |
vars5 <- c("age_Ranges", "gender2", "ethnicity2", "BMI_Ranges", "physicianSpeciality2", "icu_admit_source2", "icu_disch_location2", "hospitaldischargeyear", "dischargelocation", "dialysis", "aids", "hepaticfailure", "diabetes", "immunosuppression" , "leukemia", "lymphoma", "metastaticcancer", "thrombolytics", "sofa_respiration_baseline2", "sofa_liver_baseline2", "sofa_renal_baseline2", "cardiovascular_baseline", "group" )
library(dplyr); library(Hmisc); library(ggplot2); #library(sjPlot)
if(!("tableone" %in% rownames(installed.packages()))) {
install.packages("tableone")
}
library(dplyr); library(Hmisc); library(ggplot2); #library(sjPlot)
library(tableone)
CreateTableOne(data=ssd_incl_te ,vars=vars5,strata="qSOFA2TruthSepsis",test=FALSE, includeNA=TRUE
) %>% print(nonnormal= c("sofa_respiration_baseline", "sofa_liver_baseline", "sofa_renal_baseline"),minMax=TRUE,
printToggle = FALSE,
showAllLevels = TRUE,
cramVars = "kon"
) %>%
{data.frame(
variable_name = gsub(" ", " ", rownames(.), fixed = TRUE), .,
row.names = NULL,
check.names = FALSE,
stringsAsFactors = FALSE)} %>%
knitr::kable(caption="qSOFA positive negative sepsis_outcome")| variable_name | level | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE |
|---|---|---|---|---|---|
| n | 79553 | 137943 | 10133 | 46123 | |
| age_Ranges (%) | (0,25] | 3156 ( 4.0) | 4808 ( 3.5) | 247 ( 2.4) | 840 ( 1.8) |
| (25,35] | 4835 ( 6.1) | 7044 ( 5.1) | 511 ( 5.0) | 1670 ( 3.6) | |
| (35,45] | 7038 ( 8.8) | 10014 ( 7.3) | 716 ( 7.1) | 2560 ( 5.6) | |
| (45,55] | 12932 ( 16.3) | 20254 ( 14.7) | 1460 (14.4) | 5883 (12.8) | |
| (55,65] | 17115 ( 21.5) | 28415 ( 20.6) | 2222 (21.9) | 9352 (20.3) | |
| (65,75] | 17013 ( 21.4) | 30351 ( 22.0) | 2375 (23.4) | 10867 (23.6) | |
| (75,85] | 12777 ( 16.1) | 25324 ( 18.4) | 1842 (18.2) | 9679 (21.0) | |
| (85,100] | 4687 ( 5.9) | 11733 ( 8.5) | 760 ( 7.5) | 5272 (11.4) | |
| gender2 (%) | Male | 45645 ( 57.4) | 73018 ( 52.9) | 5252 (51.8) | 22987 (49.8) |
| Female | 33886 ( 42.6) | 64879 ( 47.0) | 4880 (48.2) | 23125 (50.1) | |
| Other/Unknown | 22 ( 0.0) | 46 ( 0.0) | 1 ( 0.0) | 11 ( 0.0) | |
| ethnicity2 (%) | Caucasian | 58577 ( 73.6) | 107468 ( 77.9) | 7447 (73.5) | 35196 (76.3) |
| African American | 10487 ( 13.2) | 15119 ( 11.0) | 1199 (11.8) | 4924 (10.7) | |
| Hispanic | 3745 ( 4.7) | 5280 ( 3.8) | 682 ( 6.7) | 2578 ( 5.6) | |
| Asian | 959 ( 1.2) | 1826 ( 1.3) | 138 ( 1.4) | 610 ( 1.3) | |
| Native American | 562 ( 0.7) | 996 ( 0.7) | 73 ( 0.7) | 381 ( 0.8) | |
| Other/Unknown | 5223 ( 6.6) | 7254 ( 5.3) | 594 ( 5.9) | 2434 ( 5.3) | |
| BMI_Ranges (%) | (0,18.5] | 2961 ( 3.7) | 6785 ( 4.9) | 542 ( 5.3) | 3160 ( 6.9) |
| (18.5,25] | 20564 ( 25.8) | 39606 ( 28.7) | 2685 (26.5) | 14020 (30.4) | |
| (25,35] | 38762 ( 48.7) | 63107 ( 45.7) | 4337 (42.8) | 19006 (41.2) | |
| (35,200] | 14063 ( 17.7) | 23575 ( 17.1) | 2212 (21.8) | 8607 (18.7) | |
| Other/Unknown | 3203 ( 4.0) | 4870 ( 3.5) | 357 ( 3.5) | 1330 ( 2.9) | |
| physicianSpeciality2 (%) | Critical Care | 16452 ( 20.7) | 41966 ( 30.4) | 3171 (31.3) | 18706 (40.6) |
| Speciality-Other | 63101 ( 79.3) | 95977 ( 69.6) | 6962 (68.7) | 27417 (59.4) | |
| icu_admit_source2 (%) | Floor | 10198 ( 12.8) | 22231 ( 16.1) | 2449 (24.2) | 11556 (25.1) |
| OR/Proc Area | 17853 ( 22.4) | 32084 ( 23.3) | 626 ( 6.2) | 2368 ( 5.1) | |
| Direct Admit | 9294 ( 11.7) | 14987 ( 10.9) | 794 ( 7.8) | 4396 ( 9.5) | |
| Emergency Department | 40542 ( 51.0) | 64550 ( 46.8) | 5938 (58.6) | 25644 (55.6) | |
| Other | 518 ( 0.7) | 1204 ( 0.9) | 91 ( 0.9) | 547 ( 1.2) | |
| Step-Down Unit | 1148 ( 1.4) | 2887 ( 2.1) | 235 ( 2.3) | 1612 ( 3.5) | |
| icu_disch_location2 (%) | Floor | 58038 ( 73.0) | 101402 ( 73.5) | 8150 (80.4) | 31829 (69.0) |
| Death | 1085 ( 1.4) | 9778 ( 7.1) | 467 ( 4.6) | 7025 (15.2) | |
| Home | 13244 ( 16.6) | 11639 ( 8.4) | 531 ( 5.2) | 1269 ( 2.8) | |
| SNF/Rehab | 754 ( 0.9) | 1894 ( 1.4) | 198 ( 2.0) | 1412 ( 3.1) | |
| Other | 1972 ( 2.5) | 4600 ( 3.3) | 299 ( 3.0) | 1934 ( 4.2) | |
| Other Hospital | 1487 ( 1.9) | 3170 ( 2.3) | 248 ( 2.4) | 1251 ( 2.7) | |
| Step-Down Unit | 2973 ( 3.7) | 5460 ( 4.0) | 240 ( 2.4) | 1403 ( 3.0) | |
| hospitaldischargeyear (%) | -2010 | 11213 ( 14.1) | 15234 ( 11.0) | 1373 (13.5) | 5528 (12.0) |
| 2011 | 10956 ( 13.8) | 17740 ( 12.9) | 1466 (14.5) | 6652 (14.4) | |
| 2012 | 12705 ( 16.0) | 23002 ( 16.7) | 1526 (15.1) | 7577 (16.4) | |
| 2013 | 14050 ( 17.7) | 26063 ( 18.9) | 1728 (17.1) | 8421 (18.3) | |
| 2014 | 15404 ( 19.4) | 27559 ( 20.0) | 2024 (20.0) | 8564 (18.6) | |
| 2015-16 | 15225 ( 19.1) | 28345 ( 20.5) | 2016 (19.9) | 9381 (20.3) | |
| dischargelocation (mean (sd)) | 5.15 (1.67) | 5.35 (1.89) | 4.91 (1.66) | 5.49 (2.07) | |
| dialysis (%) | 0 | 76924 ( 96.7) | 133622 ( 96.9) | 9715 (95.9) | 44233 (95.9) |
| 1 | 2629 ( 3.3) | 4321 ( 3.1) | 418 ( 4.1) | 1890 ( 4.1) | |
| aids (%) | 0 | 79514 (100.0) | 137877 (100.0) | 10100 (99.7) | 45998 (99.7) |
| 1 | 39 ( 0.0) | 66 ( 0.0) | 33 ( 0.3) | 125 ( 0.3) | |
| hepaticfailure (%) | FALSE | 78337 ( 98.5) | 134908 ( 97.8) | 9912 (97.8) | 44914 (97.4) |
| TRUE | 1216 ( 1.5) | 3035 ( 2.2) | 221 ( 2.2) | 1209 ( 2.6) | |
| diabetes (%) | 0 | 61305 ( 77.1) | 108663 ( 78.8) | 7670 (75.7) | 36282 (78.7) |
| 1 | 18248 ( 22.9) | 29280 ( 21.2) | 2463 (24.3) | 9841 (21.3) | |
| immunosuppression (%) | 0 | 78204 ( 98.3) | 135143 ( 98.0) | 9724 (96.0) | 44315 (96.1) |
| 1 | 1349 ( 1.7) | 2800 ( 2.0) | 409 ( 4.0) | 1808 ( 3.9) | |
| leukemia (%) | 0 | 79172 ( 99.5) | 137134 ( 99.4) | 10005 (98.7) | 45503 (98.7) |
| 1 | 381 ( 0.5) | 809 ( 0.6) | 128 ( 1.3) | 620 ( 1.3) | |
| lymphoma (%) | 0 | 79345 ( 99.7) | 137465 ( 99.7) | 10083 (99.5) | 45829 (99.4) |
| 1 | 208 ( 0.3) | 478 ( 0.3) | 50 ( 0.5) | 294 ( 0.6) | |
| metastaticcancer (%) | 0 | 78252 ( 98.4) | 135300 ( 98.1) | 9908 (97.8) | 44986 (97.5) |
| 1 | 1301 ( 1.6) | 2643 ( 1.9) | 225 ( 2.2) | 1137 ( 2.5) | |
| thrombolytics (%) | 0 | 77364 ( 97.2) | 135260 ( 98.1) | 10117 (99.8) | 46043 (99.8) |
| 1 | 2189 ( 2.8) | 2683 ( 1.9) | 16 ( 0.2) | 80 ( 0.2) | |
| sofa_respiration_baseline2 (%) | FALSE | 64499 ( 81.1) | 106326 ( 77.1) | 6459 (63.7) | 30724 (66.6) |
| TRUE | 15054 ( 18.9) | 31617 ( 22.9) | 3674 (36.3) | 15399 (33.4) | |
| sofa_liver_baseline2 (%) | FALSE | 78337 ( 98.5) | 134908 ( 97.8) | 9912 (97.8) | 44914 (97.4) |
| TRUE | 1216 ( 1.5) | 3035 ( 2.2) | 221 ( 2.2) | 1209 ( 2.6) | |
| sofa_renal_baseline2 (%) | FALSE | 76924 ( 96.7) | 133622 ( 96.9) | 9715 (95.9) | 44233 (95.9) |
| TRUE | 2629 ( 3.3) | 4321 ( 3.1) | 418 ( 4.1) | 1890 ( 4.1) | |
| cardiovascular_baseline (%) | 0 | 63290 ( 79.6) | 106022 ( 76.9) | 7729 (76.3) | 34820 (75.5) |
| 1 | 16263 ( 20.4) | 31921 ( 23.1) | 2404 (23.7) | 11303 (24.5) | |
| group (%) | Cardiovascular | 32493 ( 40.8) | 49792 ( 36.1) | 1221 (12.0) | 4857 (10.5) |
| Gastrointestinal | 9231 ( 11.6) | 15797 ( 11.5) | 722 ( 7.1) | 2794 ( 6.1) | |
| Gynaecological | 270 ( 0.3) | 412 ( 0.3) | 6 ( 0.1) | 27 ( 0.1) | |
| Hematological | 736 ( 0.9) | 1043 ( 0.8) | 77 ( 0.8) | 230 ( 0.5) | |
| Metabolic | 7826 ( 9.8) | 12786 ( 9.3) | 435 ( 4.3) | 1414 ( 3.1) | |
| Muscoskeletal/Skin disease | 1066 ( 1.3) | 1713 ( 1.2) | 141 ( 1.4) | 538 ( 1.2) | |
| Neurological | 11556 ( 14.5) | 22492 ( 16.3) | 464 ( 4.6) | 2325 ( 5.0) | |
| Renal/Genitourinary | 1860 ( 2.3) | 3229 ( 2.3) | 336 ( 3.3) | 1151 ( 2.5) | |
| Respiratory | 8318 ( 10.5) | 18635 ( 13.5) | 2640 (26.1) | 11265 (24.4) | |
| Sepsis | 748 ( 0.9) | 3502 ( 2.5) | 3989 (39.4) | 21098 (45.7) | |
| Trauma | 4584 ( 5.8) | 7227 ( 5.2) | 58 ( 0.6) | 256 ( 0.6) | |
| Undefined | 865 ( 1.1) | 1315 ( 1.0) | 44 ( 0.4) | 168 ( 0.4) |
ssd_incl_te%>%group_by(hospitaldischargeyear,qSOFA2TruthSepsis) %>%summarise(n=n())%>%spread(qSOFA2TruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| hospitaldischargeyear | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| -2010 | 11213 | 15234 | 1373 | 5528 | 0.8010433 | 0.4239800 |
| 2011 | 10956 | 17740 | 1466 | 6652 | 0.8194136 | 0.3817954 |
| 2012 | 12705 | 23002 | 1526 | 7577 | 0.8323630 | 0.3558126 |
| 2013 | 14050 | 26063 | 1728 | 8421 | 0.8297369 | 0.3502605 |
| 2014 | 15404 | 27559 | 2024 | 8564 | 0.8088402 | 0.3585411 |
| 2015-16 | 15225 | 28345 | 2016 | 9381 | 0.8231113 | 0.3494377 |
ssd_incl_te%>%group_by(age_Ranges,qSOFA2TruthSepsis) %>%summarise(n=n())%>%spread(qSOFA2TruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| age_Ranges | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| (0,25] | 3156 | 4808 | 247 | 840 | 0.7727691 | 0.3962833 |
| (25,35] | 4835 | 7044 | 511 | 1670 | 0.7657038 | 0.4070208 |
| (35,45] | 7038 | 10014 | 716 | 2560 | 0.7814408 | 0.4127375 |
| (45,55] | 12932 | 20254 | 1460 | 5883 | 0.8011712 | 0.3896824 |
| (55,65] | 17115 | 28415 | 2222 | 9352 | 0.8080180 | 0.3759060 |
| (65,75] | 17013 | 30351 | 2375 | 10867 | 0.8206464 | 0.3591969 |
| (75,85] | 12777 | 25324 | 1842 | 9679 | 0.8401180 | 0.3353455 |
| (85,100] | 4687 | 11733 | 760 | 5272 | 0.8740053 | 0.2854446 |
ssd_incl_te%>%group_by(BMI_Ranges,qSOFA2TruthSepsis) %>%summarise(n=n())%>%spread(qSOFA2TruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| BMI_Ranges | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| (0,18.5] | 2961 | 6785 | 542 | 3160 | 0.8535927 | 0.3038170 |
| (18.5,25] | 20564 | 39606 | 2685 | 14020 | 0.8392697 | 0.3417650 |
| (25,35] | 38762 | 63107 | 4337 | 19006 | 0.8142055 | 0.3805083 |
| (35,200] | 14063 | 23575 | 2212 | 8607 | 0.7955449 | 0.3736383 |
| Other/Unknown | 3203 | 4870 | 357 | 1330 | 0.7883817 | 0.3967546 |
ssd_incl_te%>%group_by(icu_admit_source2,qSOFA2TruthSepsis) %>%summarise(n=n())%>%spread(qSOFA2TruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| icu_admit_source2 | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| Floor | 10198 | 22231 | 2449 | 11556 | 0.8251339 | 0.3144716 |
| OR/Proc Area | 17853 | 32084 | 626 | 2368 | 0.7909152 | 0.3575105 |
| Direct Admit | 9294 | 14987 | 794 | 4396 | 0.8470135 | 0.3827684 |
| Emergency Department | 40542 | 64550 | 5938 | 25644 | 0.8119815 | 0.3857763 |
| Other | 518 | 1204 | 91 | 547 | 0.8573668 | 0.3008130 |
| Step-Down Unit | 1148 | 2887 | 235 | 1612 | 0.8727666 | 0.2845105 |
ssd_incl_te%>%group_by(ethnicity2,qSOFA2TruthSepsis) %>%summarise(n=n())%>%spread(qSOFA2TruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| ethnicity2 | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| Caucasian | 58577 | 107468 | 7447 | 35196 | 0.8253641 | 0.3527779 |
| African American | 10487 | 15119 | 1199 | 4924 | 0.8041810 | 0.4095524 |
| Hispanic | 3745 | 5280 | 682 | 2578 | 0.7907975 | 0.4149584 |
| Asian | 959 | 1826 | 138 | 610 | 0.8155080 | 0.3443447 |
| Native American | 562 | 996 | 73 | 381 | 0.8392070 | 0.3607189 |
| Other/Unknown | 5223 | 7254 | 594 | 2434 | 0.8038309 | 0.4186102 |
ssd_incl_te%>%group_by(physicianSpeciality2,qSOFA2TruthSepsis) %>%summarise(n=n())%>%spread(qSOFA2TruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| physicianSpeciality2 | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| Critical Care | 16452 | 41966 | 3171 | 18706 | 0.8550533 | 0.2816255 |
| Speciality-Other | 63101 | 95977 | 6962 | 27417 | 0.7974927 | 0.3966670 |
vars5 <- c("age_Ranges", "gender2", "ethnicity2", "BMI_Ranges", "physicianSpeciality2", "icu_admit_source2", "icu_disch_location2", "hospitaldischargeyear", "dischargelocation", "dialysis", "aids", "hepaticfailure", "diabetes", "immunosuppression" , "leukemia", "lymphoma", "metastaticcancer", "thrombolytics", "sofa_respiration_baseline2", "sofa_liver_baseline2", "sofa_renal_baseline2", "cardiovascular_baseline", "group" )
library(dplyr); library(Hmisc); library(ggplot2); #library(sjPlot)
if(!("tableone" %in% rownames(installed.packages()))) {
install.packages("tableone")
}
library(dplyr); library(Hmisc); library(ggplot2); #library(sjPlot)
library(tableone)
CreateTableOne(data=ssd_incl_te ,vars=vars5,strata="SOFA2TruthSepsis",test=FALSE, includeNA=TRUE
) %>% print(nonnormal= c("sofa_respiration_baseline", "sofa_liver_baseline", "sofa_renal_baseline"),minMax=TRUE,
printToggle = FALSE,
showAllLevels = TRUE,
cramVars = "kon"
) %>%
{data.frame(
variable_name = gsub(" ", " ", rownames(.), fixed = TRUE), .,
row.names = NULL,
check.names = FALSE,
stringsAsFactors = FALSE)} %>%
knitr::kable(caption="SOFA positive negative sepsis outcome")| variable_name | level | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE |
|---|---|---|---|---|---|
| n | 77471 | 140025 | 7800 | 48456 | |
| age_Ranges (%) | (0,25] | 3772 ( 4.9) | 4192 ( 3.0) | 262 ( 3.4) | 825 ( 1.7) |
| (25,35] | 5346 ( 6.9) | 6533 ( 4.7) | 501 ( 6.4) | 1680 ( 3.5) | |
| (35,45] | 7772 ( 10.0) | 9280 ( 6.6) | 609 ( 7.8) | 2667 ( 5.5) | |
| (45,55] | 13955 ( 18.0) | 19231 (13.7) | 1226 (15.7) | 6117 (12.6) | |
| (55,65] | 16991 ( 21.9) | 28539 (20.4) | 1753 (22.5) | 9821 (20.3) | |
| (65,75] | 15326 ( 19.8) | 32038 (22.9) | 1762 (22.6) | 11480 (23.7) | |
| (75,85] | 10459 ( 13.5) | 27642 (19.7) | 1194 (15.3) | 10327 (21.3) | |
| (85,100] | 3850 ( 5.0) | 12570 ( 9.0) | 493 ( 6.3) | 5539 (11.4) | |
| gender2 (%) | Male | 40185 ( 51.9) | 78478 (56.0) | 3557 (45.6) | 24682 (50.9) |
| Female | 37275 ( 48.1) | 61490 (43.9) | 4241 (54.4) | 23764 (49.0) | |
| Other/Unknown | 11 ( 0.0) | 57 ( 0.0) | 2 ( 0.0) | 10 ( 0.0) | |
| ethnicity2 (%) | Caucasian | 59028 ( 76.2) | 107017 (76.4) | 5981 (76.7) | 36662 (75.7) |
| African American | 9154 ( 11.8) | 16452 (11.7) | 823 (10.6) | 5300 (10.9) | |
| Hispanic | 3263 ( 4.2) | 5762 ( 4.1) | 447 ( 5.7) | 2813 ( 5.8) | |
| Asian | 944 ( 1.2) | 1841 ( 1.3) | 95 ( 1.2) | 653 ( 1.3) | |
| Native American | 504 ( 0.7) | 1054 ( 0.8) | 50 ( 0.6) | 404 ( 0.8) | |
| Other/Unknown | 4578 ( 5.9) | 7899 ( 5.6) | 404 ( 5.2) | 2624 ( 5.4) | |
| BMI_Ranges (%) | (0,18.5] | 3175 ( 4.1) | 6571 ( 4.7) | 566 ( 7.3) | 3136 ( 6.5) |
| (18.5,25] | 20829 ( 26.9) | 39341 (28.1) | 2330 (29.9) | 14375 (29.7) | |
| (25,35] | 36732 ( 47.4) | 65137 (46.5) | 3094 (39.7) | 20249 (41.8) | |
| (35,200] | 13439 ( 17.3) | 24199 (17.3) | 1535 (19.7) | 9284 (19.2) | |
| Other/Unknown | 3296 ( 4.3) | 4777 ( 3.4) | 275 ( 3.5) | 1412 ( 2.9) | |
| physicianSpeciality2 (%) | Critical Care | 14837 ( 19.2) | 43581 (31.1) | 2551 (32.7) | 19326 (39.9) |
| Speciality-Other | 62634 ( 80.8) | 96444 (68.9) | 5249 (67.3) | 29130 (60.1) | |
| icu_admit_source2 (%) | Floor | 9714 ( 12.5) | 22715 (16.2) | 1941 (24.9) | 12064 (24.9) |
| OR/Proc Area | 15485 ( 20.0) | 34452 (24.6) | 389 ( 5.0) | 2605 ( 5.4) | |
| Direct Admit | 9236 ( 11.9) | 15045 (10.7) | 492 ( 6.3) | 4698 ( 9.7) | |
| Emergency Department | 41469 ( 53.5) | 63623 (45.4) | 4696 (60.2) | 26886 (55.5) | |
| Other | 486 ( 0.6) | 1236 ( 0.9) | 84 ( 1.1) | 554 ( 1.1) | |
| Step-Down Unit | 1081 ( 1.4) | 2954 ( 2.1) | 198 ( 2.5) | 1649 ( 3.4) | |
| icu_disch_location2 (%) | Floor | 56350 ( 72.7) | 103090 (73.6) | 6344 (81.3) | 33635 (69.4) |
| Death | 572 ( 0.7) | 10291 ( 7.3) | 258 ( 3.3) | 7234 (14.9) | |
| Home | 14248 ( 18.4) | 10635 ( 7.6) | 453 ( 5.8) | 1347 ( 2.8) | |
| SNF/Rehab | 557 ( 0.7) | 2091 ( 1.5) | 126 ( 1.6) | 1484 ( 3.1) | |
| Other | 1944 ( 2.5) | 4628 ( 3.3) | 259 ( 3.3) | 1974 ( 4.1) | |
| Other Hospital | 1459 ( 1.9) | 3198 ( 2.3) | 170 ( 2.2) | 1329 ( 2.7) | |
| Step-Down Unit | 2341 ( 3.0) | 6092 ( 4.4) | 190 ( 2.4) | 1453 ( 3.0) | |
| hospitaldischargeyear (%) | -2010 | 9187 ( 11.9) | 17260 (12.3) | 794 (10.2) | 6107 (12.6) |
| 2011 | 9895 ( 12.8) | 18801 (13.4) | 1004 (12.9) | 7114 (14.7) | |
| 2012 | 12512 ( 16.2) | 23195 (16.6) | 1199 (15.4) | 7904 (16.3) | |
| 2013 | 14808 ( 19.1) | 25305 (18.1) | 1453 (18.6) | 8696 (17.9) | |
| 2014 | 15818 ( 20.4) | 27145 (19.4) | 1636 (21.0) | 8952 (18.5) | |
| 2015-16 | 15251 ( 19.7) | 28319 (20.2) | 1714 (22.0) | 9683 (20.0) | |
| dischargelocation (mean (sd)) | 5.23 (1.68) | 5.31 (1.89) | 4.89 (1.64) | 5.46 (2.06) | |
| dialysis (%) | 0 | 74624 ( 96.3) | 135922 (97.1) | 7395 (94.8) | 46553 (96.1) |
| 1 | 2847 ( 3.7) | 4103 ( 2.9) | 405 ( 5.2) | 1903 ( 3.9) | |
| aids (%) | 0 | 77438 (100.0) | 139953 (99.9) | 7775 (99.7) | 48323 (99.7) |
| 1 | 33 ( 0.0) | 72 ( 0.1) | 25 ( 0.3) | 133 ( 0.3) | |
| hepaticfailure (%) | FALSE | 76815 ( 99.2) | 136430 (97.4) | 7727 (99.1) | 47099 (97.2) |
| TRUE | 656 ( 0.8) | 3595 ( 2.6) | 73 ( 0.9) | 1357 ( 2.8) | |
| diabetes (%) | 0 | 61213 ( 79.0) | 108755 (77.7) | 6161 (79.0) | 37791 (78.0) |
| 1 | 16258 ( 21.0) | 31270 (22.3) | 1639 (21.0) | 10665 (22.0) | |
| immunosuppression (%) | 0 | 76228 ( 98.4) | 137119 (97.9) | 7500 (96.2) | 46539 (96.0) |
| 1 | 1243 ( 1.6) | 2906 ( 2.1) | 300 ( 3.8) | 1917 ( 4.0) | |
| leukemia (%) | 0 | 77222 ( 99.7) | 139084 (99.3) | 7746 (99.3) | 47762 (98.6) |
| 1 | 249 ( 0.3) | 941 ( 0.7) | 54 ( 0.7) | 694 ( 1.4) | |
| lymphoma (%) | 0 | 77301 ( 99.8) | 139509 (99.6) | 7770 (99.6) | 48142 (99.4) |
| 1 | 170 ( 0.2) | 516 ( 0.4) | 30 ( 0.4) | 314 ( 0.6) | |
| metastaticcancer (%) | 0 | 76182 ( 98.3) | 137370 (98.1) | 7638 (97.9) | 47256 (97.5) |
| 1 | 1289 ( 1.7) | 2655 ( 1.9) | 162 ( 2.1) | 1200 ( 2.5) | |
| thrombolytics (%) | 0 | 74789 ( 96.5) | 137835 (98.4) | 7793 (99.9) | 48367 (99.8) |
| 1 | 2682 ( 3.5) | 2190 ( 1.6) | 7 ( 0.1) | 89 ( 0.2) | |
| sofa_respiration_baseline2 (%) | FALSE | 61018 ( 78.8) | 109807 (78.4) | 4142 (53.1) | 33041 (68.2) |
| TRUE | 16453 ( 21.2) | 30218 (21.6) | 3658 (46.9) | 15415 (31.8) | |
| sofa_liver_baseline2 (%) | FALSE | 76815 ( 99.2) | 136430 (97.4) | 7727 (99.1) | 47099 (97.2) |
| TRUE | 656 ( 0.8) | 3595 ( 2.6) | 73 ( 0.9) | 1357 ( 2.8) | |
| sofa_renal_baseline2 (%) | FALSE | 74624 ( 96.3) | 135922 (97.1) | 7395 (94.8) | 46553 (96.1) |
| TRUE | 2847 ( 3.7) | 4103 ( 2.9) | 405 ( 5.2) | 1903 ( 3.9) | |
| cardiovascular_baseline (%) | 0 | 63736 ( 82.3) | 105576 (75.4) | 6152 (78.9) | 36397 (75.1) |
| 1 | 13735 ( 17.7) | 34449 (24.6) | 1648 (21.1) | 12059 (24.9) | |
| group (%) | Cardiovascular | 30306 ( 39.1) | 51979 (37.1) | 817 (10.5) | 5261 (10.9) |
| Gastrointestinal | 7801 ( 10.1) | 17227 (12.3) | 407 ( 5.2) | 3109 ( 6.4) | |
| Gynaecological | 261 ( 0.3) | 421 ( 0.3) | 5 ( 0.1) | 28 ( 0.1) | |
| Hematological | 455 ( 0.6) | 1324 ( 0.9) | 33 ( 0.4) | 274 ( 0.6) | |
| Metabolic | 8310 ( 10.7) | 12302 ( 8.8) | 274 ( 3.5) | 1575 ( 3.3) | |
| Muscoskeletal/Skin disease | 1086 ( 1.4) | 1693 ( 1.2) | 127 ( 1.6) | 552 ( 1.1) | |
| Neurological | 12518 ( 16.2) | 21530 (15.4) | 292 ( 3.7) | 2497 ( 5.2) | |
| Renal/Genitourinary | 886 ( 1.1) | 4203 ( 3.0) | 109 ( 1.4) | 1378 ( 2.8) | |
| Respiratory | 9883 ( 12.8) | 17070 (12.2) | 2882 (36.9) | 11023 (22.7) | |
| Sepsis | 787 ( 1.0) | 3463 ( 2.5) | 2783 (35.7) | 22304 (46.0) | |
| Trauma | 4145 ( 5.4) | 7666 ( 5.5) | 31 ( 0.4) | 283 ( 0.6) | |
| Undefined | 1033 ( 1.3) | 1147 ( 0.8) | 40 ( 0.5) | 172 ( 0.4) |
library(tidyr)
ssd_incl_te%>%group_by(hospitaldischargeyear,SOFA2TruthSepsis) %>%summarise(n=n())%>%spread(SOFA2TruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| hospitaldischargeyear | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| -2010 | 9187 | 17260 | 794 | 6107 | 0.8849442 | 0.3473740 |
| 2011 | 9895 | 18801 | 1004 | 7114 | 0.8763242 | 0.3448216 |
| 2012 | 12512 | 23195 | 1199 | 7904 | 0.8682852 | 0.3504075 |
| 2013 | 14808 | 25305 | 1453 | 8696 | 0.8568332 | 0.3691571 |
| 2014 | 15818 | 27145 | 1636 | 8952 | 0.8454855 | 0.3681773 |
| 2015-16 | 15251 | 28319 | 1714 | 9683 | 0.8496095 | 0.3500344 |
ssd_incl_te%>%group_by(age_Ranges,SOFA2TruthSepsis) %>%summarise(n=n())%>%spread(SOFA2TruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| age_Ranges | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| (0,25] | 3772 | 4192 | 262 | 825 | 0.7589696 | 0.4736313 |
| (25,35] | 5346 | 6533 | 501 | 1680 | 0.7702889 | 0.4500379 |
| (35,45] | 7772 | 9280 | 609 | 2667 | 0.8141026 | 0.4557823 |
| (45,55] | 13955 | 19231 | 1226 | 6117 | 0.8330383 | 0.4205086 |
| (55,65] | 16991 | 28539 | 1753 | 9821 | 0.8485398 | 0.3731825 |
| (65,75] | 15326 | 32038 | 1762 | 11480 | 0.8669385 | 0.3235791 |
| (75,85] | 10459 | 27642 | 1194 | 10327 | 0.8963632 | 0.2745072 |
| (85,100] | 3850 | 12570 | 493 | 5539 | 0.9182692 | 0.2344702 |
ssd_incl_te%>%group_by(BMI_Ranges,SOFA2TruthSepsis) %>%summarise(n=n())%>%spread(SOFA2TruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| BMI_Ranges | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| (0,18.5] | 3175 | 6571 | 566 | 3136 | 0.8471097 | 0.3257747 |
| (18.5,25] | 20829 | 39341 | 2330 | 14375 | 0.8605208 | 0.3461692 |
| (25,35] | 36732 | 65137 | 3094 | 20249 | 0.8674549 | 0.3605807 |
| (35,200] | 13439 | 24199 | 1535 | 9284 | 0.8581200 | 0.3570594 |
| Other/Unknown | 3296 | 4777 | 275 | 1412 | 0.8369887 | 0.4082745 |
ssd_incl_te%>%group_by(icu_admit_source2,SOFA2TruthSepsis) %>%summarise(n=n())%>%spread(SOFA2TruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| icu_admit_source2 | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| Floor | 9714 | 22715 | 1941 | 12064 | 0.8614066 | 0.2995467 |
| OR/Proc Area | 15485 | 34452 | 389 | 2605 | 0.8700735 | 0.3100907 |
| Direct Admit | 9236 | 15045 | 492 | 4698 | 0.9052023 | 0.3803797 |
| Emergency Department | 41469 | 63623 | 4696 | 26886 | 0.8513077 | 0.3945971 |
| Other | 486 | 1236 | 84 | 554 | 0.8683386 | 0.2822300 |
| Step-Down Unit | 1081 | 2954 | 198 | 1649 | 0.8927991 | 0.2679058 |
ssd_incl_te%>%group_by(ethnicity2,SOFA2TruthSepsis) %>%summarise(n=n())%>%spread(SOFA2TruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| ethnicity2 | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| Caucasian | 59028 | 107017 | 5981 | 36662 | 0.8597425 | 0.3554940 |
| African American | 9154 | 16452 | 823 | 5300 | 0.8655888 | 0.3574943 |
| Hispanic | 3263 | 5762 | 447 | 2813 | 0.8628834 | 0.3615512 |
| Asian | 944 | 1841 | 95 | 653 | 0.8729947 | 0.3389587 |
| Native American | 504 | 1054 | 50 | 404 | 0.8898678 | 0.3234917 |
| Other/Unknown | 4578 | 7899 | 404 | 2624 | 0.8665786 | 0.3669151 |
ssd_incl_te%>%group_by(physicianSpeciality2,SOFA2TruthSepsis) %>%summarise(n=n())%>%spread(SOFA2TruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| physicianSpeciality2 | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| Critical Care | 14837 | 43581 | 2551 | 19326 | 0.8833935 | 0.2539799 |
| Speciality-Other | 62634 | 96444 | 5249 | 29130 | 0.8473196 | 0.3937314 |
vars5 <- c("age_Ranges", "gender2", "ethnicity2", "BMI_Ranges", "physicianSpeciality2", "icu_admit_source2", "icu_disch_location2", "hospitaldischargeyear", "dischargelocation", "dialysis", "aids", "hepaticfailure", "diabetes", "immunosuppression" , "leukemia", "lymphoma", "metastaticcancer", "thrombolytics", "sofa_respiration_baseline2", "sofa_liver_baseline2", "sofa_renal_baseline2", "cardiovascular_baseline", "group" )
library(dplyr); library(Hmisc); library(ggplot2); #library(sjPlot)
if(!("tableone" %in% rownames(installed.packages()))) {
install.packages("tableone")
}
library(dplyr); library(Hmisc); library(ggplot2); #library(sjPlot)
library(tableone)
CreateTableOne(data=ssd_incl_te ,vars=vars5,strata="FuzzyLogicTruthSepsis",test=FALSE, includeNA=TRUE
) %>% print(nonnormal= c("sofa_respiration_baseline", "sofa_liver_baseline", "sofa_renal_baseline"),minMax=TRUE,
printToggle = FALSE,
showAllLevels = TRUE,
cramVars = "kon"
) %>%
{data.frame(
variable_name = gsub(" ", " ", rownames(.), fixed = TRUE), .,
row.names = NULL,
check.names = FALSE,
stringsAsFactors = FALSE)} %>%
knitr::kable(caption="FuzzyLogic positive negative sepsis outcome")| variable_name | level | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE |
|---|---|---|---|---|---|
| n | 112558 | 104938 | 10372 | 45884 | |
| age_Ranges (%) | (0,25] | 3831 ( 3.4) | 4133 ( 3.9) | 192 ( 1.9) | 895 ( 2.0) |
| (25,35] | 6258 ( 5.6) | 5621 ( 5.4) | 407 ( 3.9) | 1774 ( 3.9) | |
| (35,45] | 9317 ( 8.3) | 7735 ( 7.4) | 622 ( 6.0) | 2654 ( 5.8) | |
| (45,55] | 17833 (15.8) | 15353 ( 14.6) | 1381 (13.3) | 5962 (13.0) | |
| (55,65] | 23682 (21.0) | 21848 ( 20.8) | 2171 (20.9) | 9403 (20.5) | |
| (65,75] | 24038 (21.4) | 23326 ( 22.2) | 2475 (23.9) | 10767 (23.5) | |
| (75,85] | 19205 (17.1) | 18896 ( 18.0) | 2085 (20.1) | 9436 (20.6) | |
| (85,100] | 8394 ( 7.5) | 8026 ( 7.6) | 1039 (10.0) | 4993 (10.9) | |
| gender2 (%) | Male | 62445 (55.5) | 56218 ( 53.6) | 5331 (51.4) | 22908 (49.9) |
| Female | 50090 (44.5) | 48675 ( 46.4) | 5038 (48.6) | 22967 (50.1) | |
| Other/Unknown | 23 ( 0.0) | 45 ( 0.0) | 3 ( 0.0) | 9 ( 0.0) | |
| ethnicity2 (%) | Caucasian | 84661 (75.2) | 81384 ( 77.6) | 7718 (74.4) | 34925 (76.1) |
| African American | 14257 (12.7) | 11349 ( 10.8) | 1321 (12.7) | 4802 (10.5) | |
| Hispanic | 4791 ( 4.3) | 4234 ( 4.0) | 608 ( 5.9) | 2652 ( 5.8) | |
| Asian | 1526 ( 1.4) | 1259 ( 1.2) | 117 ( 1.1) | 631 ( 1.4) | |
| Native American | 805 ( 0.7) | 753 ( 0.7) | 79 ( 0.8) | 375 ( 0.8) | |
| Other/Unknown | 6518 ( 5.8) | 5959 ( 5.7) | 529 ( 5.1) | 2499 ( 5.4) | |
| BMI_Ranges (%) | (0,18.5] | 4542 ( 4.0) | 5204 ( 5.0) | 593 ( 5.7) | 3109 ( 6.8) |
| (18.5,25] | 30572 (27.2) | 29598 ( 28.2) | 2894 (27.9) | 13811 (30.1) | |
| (25,35] | 53815 (47.8) | 48054 ( 45.8) | 4301 (41.5) | 19042 (41.5) | |
| (35,200] | 18893 (16.8) | 18745 ( 17.9) | 2195 (21.2) | 8624 (18.8) | |
| Other/Unknown | 4736 ( 4.2) | 3337 ( 3.2) | 389 ( 3.8) | 1298 ( 2.8) | |
| physicianSpeciality2 (%) | Critical Care | 23765 (21.1) | 34653 ( 33.0) | 3459 (33.3) | 18418 (40.1) |
| Speciality-Other | 88793 (78.9) | 70285 ( 67.0) | 6913 (66.7) | 27466 (59.9) | |
| icu_admit_source2 (%) | Floor | 15639 (13.9) | 16790 ( 16.0) | 2919 (28.1) | 11086 (24.2) |
| OR/Proc Area | 22390 (19.9) | 27547 ( 26.3) | 589 ( 5.7) | 2405 ( 5.2) | |
| Direct Admit | 14914 (13.3) | 9367 ( 8.9) | 1063 (10.2) | 4127 ( 9.0) | |
| Emergency Department | 56909 (50.6) | 48183 ( 45.9) | 5225 (50.4) | 26357 (57.4) | |
| Other | 862 ( 0.8) | 860 ( 0.8) | 156 ( 1.5) | 482 ( 1.1) | |
| Step-Down Unit | 1844 ( 1.6) | 2191 ( 2.1) | 420 ( 4.0) | 1427 ( 3.1) | |
| icu_disch_location2 (%) | Floor | 82010 (72.9) | 77430 ( 73.8) | 8231 (79.4) | 31748 (69.2) |
| Death | 1594 ( 1.4) | 9269 ( 8.8) | 389 ( 3.8) | 7103 (15.5) | |
| Home | 18696 (16.6) | 6187 ( 5.9) | 536 ( 5.2) | 1264 ( 2.8) | |
| SNF/Rehab | 1207 ( 1.1) | 1441 ( 1.4) | 269 ( 2.6) | 1341 ( 2.9) | |
| Other | 3233 ( 2.9) | 3339 ( 3.2) | 361 ( 3.5) | 1872 ( 4.1) | |
| Other Hospital | 2217 ( 2.0) | 2440 ( 2.3) | 249 ( 2.4) | 1250 ( 2.7) | |
| Step-Down Unit | 3601 ( 3.2) | 4832 ( 4.6) | 337 ( 3.2) | 1306 ( 2.8) | |
| hospitaldischargeyear (%) | -2010 | 13636 (12.1) | 12811 ( 12.2) | 1155 (11.1) | 5746 (12.5) |
| 2011 | 14634 (13.0) | 14062 ( 13.4) | 1365 (13.2) | 6753 (14.7) | |
| 2012 | 18350 (16.3) | 17357 ( 16.5) | 1581 (15.2) | 7522 (16.4) | |
| 2013 | 20936 (18.6) | 19177 ( 18.3) | 1906 (18.4) | 8243 (18.0) | |
| 2014 | 22558 (20.0) | 20405 ( 19.4) | 2090 (20.2) | 8498 (18.5) | |
| 2015-16 | 22444 (19.9) | 21126 ( 20.1) | 2275 (21.9) | 9122 (19.9) | |
| dischargelocation (mean (sd)) | 5.22 (1.70) | 5.34 (1.93) | 4.99 (1.70) | 5.47 (2.07) | |
| dialysis (%) | 0 | 108683 (96.6) | 101863 ( 97.1) | 9843 (94.9) | 44105 (96.1) |
| 1 | 3875 ( 3.4) | 3075 ( 2.9) | 529 ( 5.1) | 1779 ( 3.9) | |
| aids (%) | 0 | 112497 (99.9) | 104894 (100.0) | 10332 (99.6) | 45766 (99.7) |
| 1 | 61 ( 0.1) | 44 ( 0.0) | 40 ( 0.4) | 118 ( 0.3) | |
| hepaticfailure (%) | FALSE | 111225 (98.8) | 102020 ( 97.2) | 10184 (98.2) | 44642 (97.3) |
| TRUE | 1333 ( 1.2) | 2918 ( 2.8) | 188 ( 1.8) | 1242 ( 2.7) | |
| diabetes (%) | 0 | 85076 (75.6) | 84892 ( 80.9) | 7122 (68.7) | 36830 (80.3) |
| 1 | 27482 (24.4) | 20046 ( 19.1) | 3250 (31.3) | 9054 (19.7) | |
| immunosuppression (%) | 0 | 110806 (98.4) | 102541 ( 97.7) | 9998 (96.4) | 44041 (96.0) |
| 1 | 1752 ( 1.6) | 2397 ( 2.3) | 374 ( 3.6) | 1843 ( 4.0) | |
| leukemia (%) | 0 | 112074 (99.6) | 104232 ( 99.3) | 10244 (98.8) | 45264 (98.6) |
| 1 | 484 ( 0.4) | 706 ( 0.7) | 128 ( 1.2) | 620 ( 1.4) | |
| lymphoma (%) | 0 | 112246 (99.7) | 104564 ( 99.6) | 10321 (99.5) | 45591 (99.4) |
| 1 | 312 ( 0.3) | 374 ( 0.4) | 51 ( 0.5) | 293 ( 0.6) | |
| metastaticcancer (%) | 0 | 110816 (98.5) | 102736 ( 97.9) | 10162 (98.0) | 44732 (97.5) |
| 1 | 1742 ( 1.5) | 2202 ( 2.1) | 210 ( 2.0) | 1152 ( 2.5) | |
| thrombolytics (%) | 0 | 109282 (97.1) | 103342 ( 98.5) | 10356 (99.8) | 45804 (99.8) |
| 1 | 3276 ( 2.9) | 1596 ( 1.5) | 16 ( 0.2) | 80 ( 0.2) | |
| sofa_respiration_baseline2 (%) | FALSE | 91478 (81.3) | 79347 ( 75.6) | 6619 (63.8) | 30564 (66.6) |
| TRUE | 21080 (18.7) | 25591 ( 24.4) | 3753 (36.2) | 15320 (33.4) | |
| sofa_liver_baseline2 (%) | FALSE | 111225 (98.8) | 102020 ( 97.2) | 10184 (98.2) | 44642 (97.3) |
| TRUE | 1333 ( 1.2) | 2918 ( 2.8) | 188 ( 1.8) | 1242 ( 2.7) | |
| sofa_renal_baseline2 (%) | FALSE | 108683 (96.6) | 101863 ( 97.1) | 9843 (94.9) | 44105 (96.1) |
| TRUE | 3875 ( 3.4) | 3075 ( 2.9) | 529 ( 5.1) | 1779 ( 3.9) | |
| cardiovascular_baseline (%) | 0 | 88247 (78.4) | 81065 ( 77.3) | 7585 (73.1) | 34964 (76.2) |
| 1 | 24311 (21.6) | 23873 ( 22.7) | 2787 (26.9) | 10920 (23.8) | |
| group (%) | Cardiovascular | 45657 (40.6) | 36628 ( 34.9) | 1376 (13.3) | 4702 (10.2) |
| Gastrointestinal | 10269 ( 9.1) | 14759 ( 14.1) | 576 ( 5.6) | 2940 ( 6.4) | |
| Gynaecological | 241 ( 0.2) | 441 ( 0.4) | 7 ( 0.1) | 26 ( 0.1) | |
| Hematological | 810 ( 0.7) | 969 ( 0.9) | 64 ( 0.6) | 243 ( 0.5) | |
| Metabolic | 10717 ( 9.5) | 9895 ( 9.4) | 429 ( 4.1) | 1420 ( 3.1) | |
| Muscoskeletal/Skin disease | 1404 ( 1.2) | 1375 ( 1.3) | 150 ( 1.4) | 529 ( 1.2) | |
| Neurological | 22038 (19.6) | 12010 ( 11.4) | 796 ( 7.7) | 1993 ( 4.3) | |
| Renal/Genitourinary | 2428 ( 2.2) | 2661 ( 2.5) | 363 ( 3.5) | 1124 ( 2.4) | |
| Respiratory | 11009 ( 9.8) | 15944 ( 15.2) | 3127 (30.1) | 10778 (23.5) | |
| Sepsis | 949 ( 0.8) | 3301 ( 3.1) | 3370 (32.5) | 21717 (47.3) | |
| Trauma | 5862 ( 5.2) | 5949 ( 5.7) | 63 ( 0.6) | 251 ( 0.5) | |
| Undefined | 1174 ( 1.0) | 1006 ( 1.0) | 51 ( 0.5) | 161 ( 0.4) |
library(tidyr)
ssd_incl_te%>%group_by(hospitaldischargeyear,FuzzyLogicTruthSepsis) %>%summarise(n=n())%>%spread(FuzzyLogicTruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| hospitaldischargeyear | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| -2010 | 13636 | 12811 | 1155 | 5746 | 0.8326330 | 0.5155972 |
| 2011 | 14634 | 14062 | 1365 | 6753 | 0.8318551 | 0.5099665 |
| 2012 | 18350 | 17357 | 1581 | 7522 | 0.8263210 | 0.5139048 |
| 2013 | 20936 | 19177 | 1906 | 8243 | 0.8121982 | 0.5219256 |
| 2014 | 22558 | 20405 | 2090 | 8498 | 0.8026067 | 0.5250564 |
| 2015-16 | 22444 | 21126 | 2275 | 9122 | 0.8003861 | 0.5151251 |
ssd_incl_te%>%group_by(age_Ranges,FuzzyLogicTruthSepsis) %>%summarise(n=n())%>%spread(FuzzyLogicTruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| age_Ranges | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| (0,25] | 3831 | 4133 | 192 | 895 | 0.8233671 | 0.4810397 |
| (25,35] | 6258 | 5621 | 407 | 1774 | 0.8133884 | 0.5268120 |
| (35,45] | 9317 | 7735 | 622 | 2654 | 0.8101343 | 0.5463875 |
| (45,55] | 17833 | 15353 | 1381 | 5962 | 0.8119297 | 0.5373652 |
| (55,65] | 23682 | 21848 | 2171 | 9403 | 0.8124244 | 0.5201406 |
| (65,75] | 24038 | 23326 | 2475 | 10767 | 0.8130947 | 0.5075163 |
| (75,85] | 19205 | 18896 | 2085 | 9436 | 0.8190261 | 0.5040550 |
| (85,100] | 8394 | 8026 | 1039 | 4993 | 0.8277520 | 0.5112058 |
ssd_incl_te%>%group_by(BMI_Ranges,FuzzyLogicTruthSepsis) %>%summarise(n=n())%>%spread(FuzzyLogicTruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| BMI_Ranges | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| (0,18.5] | 4542 | 5204 | 593 | 3109 | 0.8398163 | 0.4660373 |
| (18.5,25] | 30572 | 29598 | 2894 | 13811 | 0.8267585 | 0.5080937 |
| (25,35] | 53815 | 48054 | 4301 | 19042 | 0.8157478 | 0.5282765 |
| (35,200] | 18893 | 18745 | 2195 | 8624 | 0.7971162 | 0.5019661 |
| Other/Unknown | 4736 | 3337 | 389 | 1298 | 0.7694132 | 0.5866468 |
ssd_incl_te%>%group_by(icu_admit_source2,FuzzyLogicTruthSepsis) %>%summarise(n=n())%>%spread(FuzzyLogicTruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| icu_admit_source2 | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| Floor | 15639 | 16790 | 2919 | 11086 | 0.7915744 | 0.4822535 |
| OR/Proc Area | 22390 | 27547 | 589 | 2405 | 0.8032732 | 0.4483649 |
| Direct Admit | 14914 | 9367 | 1063 | 4127 | 0.7951830 | 0.6142251 |
| Emergency Department | 56909 | 48183 | 5225 | 26357 | 0.8345577 | 0.5415160 |
| Other | 862 | 860 | 156 | 482 | 0.7554859 | 0.5005807 |
| Step-Down Unit | 1844 | 2191 | 420 | 1427 | 0.7726042 | 0.4570012 |
ssd_incl_te%>%group_by(ethnicity2,FuzzyLogicTruthSepsis) %>%summarise(n=n())%>%spread(FuzzyLogicTruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| ethnicity2 | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| Caucasian | 84661 | 81384 | 7718 | 34925 | 0.8190090 | 0.5098678 |
| African American | 14257 | 11349 | 1321 | 4802 | 0.7842561 | 0.5567836 |
| Hispanic | 4791 | 4234 | 608 | 2652 | 0.8134969 | 0.5308587 |
| Asian | 1526 | 1259 | 117 | 631 | 0.8435829 | 0.5479354 |
| Native American | 805 | 753 | 79 | 375 | 0.8259912 | 0.5166881 |
| Other/Unknown | 6518 | 5959 | 529 | 2499 | 0.8252972 | 0.5224012 |
ssd_incl_te%>%group_by(physicianSpeciality2,FuzzyLogicTruthSepsis) %>%summarise(n=n())%>%spread(FuzzyLogicTruthSepsis,n)%>%mutate(SENS=TRUE.TRUE/(TRUE.TRUE+FALSE.TRUE),SPEC=FALSE.FALSE/(FALSE.FALSE+TRUE.FALSE))%>%knitr::kable()| physicianSpeciality2 | FALSE.FALSE | TRUE.FALSE | FALSE.TRUE | TRUE.TRUE | SENS | SPEC |
|---|---|---|---|---|---|---|
| Critical Care | 23765 | 34653 | 3459 | 18418 | 0.8418887 | 0.4068095 |
| Speciality-Other | 88793 | 70285 | 6913 | 27466 | 0.7989179 | 0.5581727 |
24 Table 1 Before inclusion/exclusion
varsTable1 <- c("age", "gender2", "ethnicity2", "BMI_Ranges", "icu_admit_source2","physicianSpeciality2", "hospitaldischargeyear", "hospital_teaching_status", "hospital_size", "hospital_region2","dialysis", "aids", "hepaticfailure", "diabetes", "immunosuppression", "leukemia", "lymphoma", "metastaticcancer", "thrombolytics", "sofa_respiration_baseline2", "cardiovascular_baseline","SIRS_Positive", "qSOFA_Positive", "SOFA_Positive", "SepsisFuzzyLogicPositive","apacheiva", "hospital_mortality_ultimate", "icu_mortality", "hospital_los", "icu_los","sepsis_outcome", "group")
library(dplyr); library(Hmisc); library(ggplot2); library(sjPlot)
if(!("tableone" %in% rownames(installed.packages()))) {
install.packages("tableone")
}
library(tableone)
CreateTableOne(data=ssd ,vars=varsTable1,strata="hospital_mortality_ultimate",test=TRUE, includeNA=TRUE
) %>% print(nonnormal= c("icu_mortality", "sepsis_outcome","hospital_teaching_status"),minMax=TRUE,
printToggle = FALSE,
showAllLevels = TRUE,
cramVars = "kon"
) %>%
{data.frame(
variable_name = gsub(" ", " ", rownames(.), fixed = TRUE), .,
row.names = NULL,
check.names = FALSE,
stringsAsFactors = FALSE)} %>%
knitr::kable(caption= "Demographic, Severity of Illness, Diagnostic, and Outcome Data")| variable_name | level | 0 | 1 | p | test |
|---|---|---|---|---|---|
| n | 2200750 | 236690 | |||
| age (mean (sd)) | 61.97 (17.51) | 69.72 (15.00) | <0.001 | ||
| gender2 (%) | Male | 1185691 ( 53.9) | 125568 ( 53.1) | <0.001 | |
| Female | 1011585 ( 46.0) | 110708 ( 46.8) | |||
| Other/Unknown | 3474 ( 0.2) | 414 ( 0.2) | |||
| ethnicity2 (%) | Caucasian | 1662178 ( 75.5) | 179335 ( 75.8) | <0.001 | |
| African American | 241932 ( 11.0) | 25446 ( 10.8) | |||
| Hispanic | 109661 ( 5.0) | 11284 ( 4.8) | |||
| Asian | 34728 ( 1.6) | 4497 ( 1.9) | |||
| Native American | 17674 ( 0.8) | 1689 ( 0.7) | |||
| Other/Unknown | 134577 ( 6.1) | 14439 ( 6.1) | |||
| BMI_Ranges (%) | (0,18.5] | 99308 ( 4.5) | 17010 ( 7.2) | <0.001 | |
| (18.5,25] | 607267 ( 27.6) | 74018 ( 31.3) | |||
| (25,35] | 981253 ( 44.6) | 90336 ( 38.2) | |||
| (35,200] | 371204 ( 16.9) | 33388 ( 14.1) | |||
| Other/Unknown | 141718 ( 6.4) | 21938 ( 9.3) | |||
| icu_admit_source2 (%) | Floor | 353263 ( 16.1) | 68254 ( 28.8) | <0.001 | |
| OR/Proc Area | 451553 ( 20.5) | 19077 ( 8.1) | |||
| Direct Admit | 209313 ( 9.5) | 23747 ( 10.0) | |||
| Emergency Department | 1078676 ( 49.0) | 108740 ( 45.9) | |||
| Other | 63717 ( 2.9) | 8765 ( 3.7) | |||
| Step-Down Unit | 44228 ( 2.0) | 8107 ( 3.4) | |||
| physicianSpeciality2 (%) | Critical Care | 411995 ( 18.7) | 61205 ( 25.9) | <0.001 | |
| Speciality-Other | 1788755 ( 81.3) | 175485 ( 74.1) | |||
| hospitaldischargeyear (%) | -2010 | 752801 ( 34.2) | 83469 ( 35.3) | <0.001 | |
| 2011 | 227837 ( 10.4) | 24579 ( 10.4) | |||
| 2012 | 260187 ( 11.8) | 27611 ( 11.7) | |||
| 2013 | 277559 ( 12.6) | 29612 ( 12.5) | |||
| 2014 | 294619 ( 13.4) | 30288 ( 12.8) | |||
| 2015-16 | 387747 ( 17.6) | 41131 ( 17.4) | |||
| hospital_teaching_status (%) | 439931 ( 20.0) | 41136 ( 17.4) | <0.001 | ||
| f | 1304606 ( 59.3) | 138608 ( 58.6) | |||
| t | 456213 ( 20.7) | 56946 ( 24.1) | |||
| hospital_size (%) | 509771 ( 23.2) | 48616 ( 20.5) | <0.001 | ||
| <100 | 111324 ( 5.1) | 8921 ( 3.8) | |||
| 100-249 | 431572 ( 19.6) | 40995 ( 17.3) | |||
| 250-500 | 376455 ( 17.1) | 41401 ( 17.5) | |||
| >500 | 771628 ( 35.1) | 96757 ( 40.9) | |||
| hospital_region2 (%) | Midwest | 622551 ( 28.3) | 64551 ( 27.3) | <0.001 | |
| Northeast | 124015 ( 5.6) | 17161 ( 7.3) | |||
| South | 565828 ( 25.7) | 69791 ( 29.5) | |||
| West | 395017 ( 17.9) | 38840 ( 16.4) | |||
| Unknown | 493339 ( 22.4) | 46347 ( 19.6) | |||
| dialysis (%) | 0 | 2124367 ( 96.5) | 224664 ( 94.9) | NaN | |
| 1 | 76383 ( 3.5) | 12026 ( 5.1) | |||
| NA | 0 ( 0.0) | 0 ( 0.0) | |||
| aids (%) | 0 | 2198348 ( 99.9) | 236188 ( 99.8) | NaN | |
| 1 | 2402 ( 0.1) | 502 ( 0.2) | |||
| NA | 0 ( 0.0) | 0 ( 0.0) | |||
| hepaticfailure (%) | FALSE | 2159154 ( 98.1) | 228258 ( 96.4) | NaN | |
| TRUE | 41596 ( 1.9) | 8432 ( 3.6) | |||
| NA | 0 ( 0.0) | 0 ( 0.0) | |||
| diabetes (%) | 0 | 1724302 ( 78.4) | 191474 ( 80.9) | NaN | |
| 1 | 476448 ( 21.6) | 45216 ( 19.1) | |||
| NA | 0 ( 0.0) | 0 ( 0.0) | |||
| immunosuppression (%) | 0 | 2155928 ( 98.0) | 226667 ( 95.8) | NaN | |
| 1 | 44822 ( 2.0) | 10023 ( 4.2) | |||
| NA | 0 ( 0.0) | 0 ( 0.0) | |||
| leukemia (%) | 0 | 2187388 ( 99.4) | 233115 ( 98.5) | NaN | |
| 1 | 13362 ( 0.6) | 3575 ( 1.5) | |||
| NA | 0 ( 0.0) | 0 ( 0.0) | |||
| lymphoma (%) | 0 | 2192810 ( 99.6) | 235019 ( 99.3) | NaN | |
| 1 | 7940 ( 0.4) | 1671 ( 0.7) | |||
| NA | 0 ( 0.0) | 0 ( 0.0) | |||
| metastaticcancer (%) | 0 | 2164132 ( 98.3) | 227609 ( 96.2) | NaN | |
| 1 | 36618 ( 1.7) | 9081 ( 3.8) | |||
| NA | 0 ( 0.0) | 0 ( 0.0) | |||
| thrombolytics (%) | 0 | 2163227 ( 98.3) | 233398 ( 98.6) | NaN | |
| 1 | 37523 ( 1.7) | 3292 ( 1.4) | |||
| NA | 0 ( 0.0) | 0 ( 0.0) | |||
| sofa_respiration_baseline2 (%) | FALSE | 1725862 ( 78.4) | 174443 ( 73.7) | <0.001 | |
| TRUE | 474888 ( 21.6) | 62247 ( 26.3) | |||
| cardiovascular_baseline (%) | 0 | 1743486 ( 79.2) | 174973 ( 73.9) | <0.001 | |
| 1 | 457264 ( 20.8) | 61717 ( 26.1) | |||
| SIRS_Positive (%) | FALSE | 662262 ( 30.1) | 29711 ( 12.6) | <0.001 | |
| TRUE | 1538488 ( 69.9) | 206979 ( 87.4) | |||
| qSOFA_Positive (%) | FALSE | 905481 ( 41.1) | 42305 ( 17.9) | <0.001 | |
| TRUE | 1295269 ( 58.9) | 194385 ( 82.1) | |||
| SOFA_Positive (%) | FALSE | 833502 ( 37.9) | 24965 ( 10.5) | <0.001 | |
| TRUE | 1367248 ( 62.1) | 211725 ( 89.5) | |||
| SepsisFuzzyLogicPositive (%) | FALSE | 1156340 ( 52.5) | 49013 ( 20.7) | <0.001 | |
| TRUE | 1044410 ( 47.5) | 187677 ( 79.3) | |||
| apacheiva (mean (sd)) | 49.53 (23.88) | 82.85 (35.21) | <0.001 | ||
| hospital_mortality_ultimate (%) | 0 | 2200750 (100.0) | 0 ( 0.0) | NaN | |
| 1 | 0 ( 0.0) | 236690 (100.0) | |||
| NA | 0 ( 0.0) | 0 ( 0.0) | |||
| icu_mortality (%) | 0 | 2197818 ( 99.9) | 97253 ( 41.1) | <0.001 | |
| 1 | 2560 ( 0.1) | 139399 ( 58.9) | |||
| NA | 372 ( 0.0) | 38 ( 0.0) | |||
| hospital_los (mean (sd)) | 8.70 (51.35) | 10.40 (100.12) | <0.001 | ||
| icu_los (mean (sd)) | 2.84 (4.10) | 4.27 (6.37) | <0.001 | ||
| sepsis_outcome (%) | FALSE | 1654616 ( 75.2) | 127568 ( 53.9) | <0.001 | |
| TRUE | 371469 ( 16.9) | 83856 ( 35.4) | |||
| NA | 174665 ( 7.9) | 25266 ( 10.7) | |||
| group (%) | Cardiovascular | 717129 ( 32.6) | 66498 ( 28.1) | <0.001 | |
| Gastrointestinal | 227007 ( 10.3) | 21653 ( 9.1) | |||
| Gynaecological | 6498 ( 0.3) | 100 ( 0.0) | |||
| Hematological | 15625 ( 0.7) | 1911 ( 0.8) | |||
| Metabolic | 181200 ( 8.2) | 3691 ( 1.6) | |||
| Muscoskeletal/Skin disease | 32042 ( 1.5) | 1584 ( 0.7) | |||
| Neurological | 275981 ( 12.5) | 27757 ( 11.7) | |||
| Renal/Genitourinary | 54223 ( 2.5) | 4372 ( 1.8) | |||
| Respiratory | 307334 ( 14.0) | 47033 ( 19.9) | |||
| Sepsis | 260337 ( 11.8) | 52266 ( 22.1) | |||
| Trauma | 98345 ( 4.5) | 7363 ( 3.1) | |||
| Undefined | 17322 ( 0.8) | 2275 ( 1.0) | |||
| NA | 7707 ( 0.4) | 187 ( 0.1) |
CreateTableOne(data=ssd ,vars=varsTable1,strata="sepsis_outcome",test=TRUE, includeNA=TRUE
) %>% print(nonnormal= c("hospital_mortality_ultimate", "icu_mortality", "hospital_teaching_status"),minMax=TRUE,
printToggle = FALSE,
showAllLevels = TRUE,
cramVars = "kon"
) %>%
{data.frame(
variable_name = gsub(" ", " ", rownames(.), fixed = TRUE), .,
row.names = NULL,
check.names = FALSE,
stringsAsFactors = FALSE)} %>%
knitr::kable(caption= "Demographic, Severity of Illness, Diagnostic, and Outcome Data")| variable_name | level | FALSE | TRUE | p | test |
|---|---|---|---|---|---|
| n | 1906183 | 485158 | |||
| age (mean (sd)) | 62.00 (17.62) | 65.33 (16.30) | <0.001 | ||
| gender2 (%) | Male | 1041537 ( 54.6) | 247071 ( 50.9) | <0.001 | |
| Female | 862802 ( 45.3) | 237856 ( 49.0) | |||
| Other/Unknown | 1844 ( 0.1) | 231 ( 0.0) | |||
| ethnicity2 (%) | Caucasian | 1440415 ( 75.6) | 362535 ( 74.7) | <0.001 | |
| African American | 209919 ( 11.0) | 54731 ( 11.3) | |||
| Hispanic | 89531 ( 4.7) | 28114 ( 5.8) | |||
| Asian | 30883 ( 1.6) | 8136 ( 1.7) | |||
| Native American | 15141 ( 0.8) | 4412 ( 0.9) | |||
| Other/Unknown | 120294 ( 6.3) | 27230 ( 5.6) | |||
| BMI_Ranges (%) | (0,18.5] | 82448 ( 4.3) | 32315 ( 6.7) | <0.001 | |
| (18.5,25] | 527106 ( 27.7) | 143582 ( 29.6) | |||
| (25,35] | 864803 ( 45.4) | 194894 ( 40.2) | |||
| (35,200] | 312118 ( 16.4) | 89639 ( 18.5) | |||
| Other/Unknown | 119708 ( 6.3) | 24728 ( 5.1) | |||
| icu_admit_source2 (%) | Floor | 274569 ( 14.4) | 118755 ( 24.5) | <0.001 | |
| OR/Proc Area | 435146 ( 22.8) | 24784 ( 5.1) | |||
| Direct Admit | 187226 ( 9.8) | 35055 ( 7.2) | |||
| Emergency Department | 881068 ( 46.2) | 263433 ( 54.3) | |||
| Other | 71673 ( 3.8) | 22718 ( 4.7) | |||
| Step-Down Unit | 56501 ( 3.0) | 20413 ( 4.2) | |||
| physicianSpeciality2 (%) | Critical Care | 319996 ( 16.8) | 120000 ( 24.7) | <0.001 | |
| Speciality-Other | 1586187 ( 83.2) | 365158 ( 75.3) | |||
| hospitaldischargeyear (%) | -2010 | 639409 ( 33.5) | 127734 ( 26.3) | <0.001 | |
| 2011 | 201908 ( 10.6) | 55907 ( 11.5) | |||
| 2012 | 232782 ( 12.2) | 63074 ( 13.0) | |||
| 2013 | 247893 ( 13.0) | 69668 ( 14.4) | |||
| 2014 | 261515 ( 13.7) | 74955 ( 15.4) | |||
| 2015-16 | 322676 ( 16.9) | 93820 ( 19.3) | |||
| hospital_teaching_status (%) | 381796 ( 20.0) | 81424 ( 16.8) | <0.001 | ||
| f | 1134725 ( 59.5) | 293910 ( 60.6) | |||
| t | 389662 ( 20.4) | 109824 ( 22.6) | |||
| hospital_size (%) | 443992 ( 23.3) | 95727 ( 19.7) | <0.001 | ||
| <100 | 80363 ( 4.2) | 30002 ( 6.2) | |||
| 100-249 | 366501 ( 19.2) | 91993 ( 19.0) | |||
| 250-500 | 314346 ( 16.5) | 95797 ( 19.7) | |||
| >500 | 700981 ( 36.8) | 171639 ( 35.4) | |||
| hospital_region2 (%) | Midwest | 527381 ( 27.7) | 123262 ( 25.4) | <0.001 | |
| Northeast | 94132 ( 4.9) | 48266 ( 9.9) | |||
| South | 500396 ( 26.3) | 127715 ( 26.3) | |||
| West | 343530 ( 18.0) | 95658 ( 19.7) | |||
| Unknown | 440744 ( 23.1) | 90257 ( 18.6) | |||
| dialysis (%) | 0 | 1721090 ( 90.3) | 433406 ( 89.3) | <0.001 | |
| 1 | 61094 ( 3.2) | 21919 ( 4.5) | |||
| NA | 123999 ( 6.5) | 29833 ( 6.1) | |||
| aids (%) | 0 | 1781020 ( 93.4) | 453749 ( 93.5) | <0.001 | |
| 1 | 1164 ( 0.1) | 1576 ( 0.3) | |||
| NA | 123999 ( 6.5) | 29833 ( 6.1) | |||
| hepaticfailure (%) | FALSE | 1747642 ( 91.7) | 442751 ( 91.3) | <0.001 | |
| TRUE | 34542 ( 1.8) | 12574 ( 2.6) | |||
| NA | 123999 ( 6.5) | 29833 ( 6.1) | |||
| diabetes (%) | 0 | 1393143 ( 73.1) | 351921 ( 72.5) | <0.001 | |
| 1 | 389041 ( 20.4) | 103404 ( 21.3) | |||
| NA | 123999 ( 6.5) | 29833 ( 6.1) | |||
| immunosuppression (%) | 0 | 1748852 ( 91.7) | 437507 ( 90.2) | <0.001 | |
| 1 | 33332 ( 1.7) | 17818 ( 3.7) | |||
| NA | 123999 ( 6.5) | 29833 ( 6.1) | |||
| leukemia (%) | 0 | 1772097 ( 93.0) | 449469 ( 92.6) | <0.001 | |
| 1 | 10087 ( 0.5) | 5856 ( 1.2) | |||
| NA | 123999 ( 6.5) | 29833 ( 6.1) | |||
| lymphoma (%) | 0 | 1776216 ( 93.2) | 452286 ( 93.2) | <0.001 | |
| 1 | 5968 ( 0.3) | 3039 ( 0.6) | |||
| NA | 123999 ( 6.5) | 29833 ( 6.1) | |||
| metastaticcancer (%) | 0 | 1750410 ( 91.8) | 444166 ( 91.6) | <0.001 | |
| 1 | 31774 ( 1.7) | 11159 ( 2.3) | |||
| NA | 123999 ( 6.5) | 29833 ( 6.1) | |||
| thrombolytics (%) | 0 | 1744509 ( 91.5) | 454375 ( 93.7) | <0.001 | |
| 1 | 37675 ( 2.0) | 950 ( 0.2) | |||
| NA | 123999 ( 6.5) | 29833 ( 6.1) | |||
| sofa_respiration_baseline2 (%) | FALSE | 1519390 ( 79.7) | 324930 ( 67.0) | <0.001 | |
| TRUE | 386793 ( 20.3) | 160228 ( 33.0) | |||
| cardiovascular_baseline (%) | 0 | 1500867 ( 78.7) | 370111 ( 76.3) | <0.001 | |
| 1 | 405316 ( 21.3) | 115047 ( 23.7) | |||
| SIRS_Positive (%) | FALSE | 604594 ( 31.7) | 67054 ( 13.8) | <0.001 | |
| TRUE | 1301589 ( 68.3) | 418104 ( 86.2) | |||
| qSOFA_Positive (%) | FALSE | 824832 ( 43.3) | 117284 ( 24.2) | <0.001 | |
| TRUE | 1081351 ( 56.7) | 367874 ( 75.8) | |||
| SOFA_Positive (%) | FALSE | 763287 ( 40.0) | 85809 ( 17.7) | <0.001 | |
| TRUE | 1142896 ( 60.0) | 399349 ( 82.3) | |||
| SepsisFuzzyLogicPositive (%) | FALSE | 1064503 ( 55.8) | 108422 ( 22.3) | <0.001 | |
| TRUE | 841680 ( 44.2) | 376736 ( 77.7) | |||
| apacheiva (mean (sd)) | 49.62 (24.87) | 67.19 (28.91) | <0.001 | ||
| hospital_mortality_ultimate (%) | 0 | 1654616 ( 86.8) | 371469 ( 76.6) | <0.001 | |
| 1 | 127568 ( 6.7) | 83856 ( 17.3) | |||
| NA | 123999 ( 6.5) | 29833 ( 6.1) | |||
| icu_mortality (%) | 0 | 1825421 ( 95.8) | 430566 ( 88.7) | <0.001 | |
| 1 | 80536 ( 4.2) | 54546 ( 11.2) | |||
| NA | 226 ( 0.0) | 46 ( 0.0) | |||
| hospital_los (mean (sd)) | 7.91 (60.18) | 12.00 (35.87) | <0.001 | ||
| icu_los (mean (sd)) | 2.66 (3.89) | 4.05 (5.37) | <0.001 | ||
| sepsis_outcome (%) | FALSE | 1906183 (100.0) | 0 ( 0.0) | NaN | |
| TRUE | 0 ( 0.0) | 485158 (100.0) | |||
| NA | 0 ( 0.0) | 0 ( 0.0) | |||
| group (%) | Cardiovascular | 731047 ( 38.4) | 53266 ( 11.0) | <0.001 | |
| Gastrointestinal | 217852 ( 11.4) | 30809 ( 6.4) | |||
| Gynaecological | 6226 ( 0.3) | 287 ( 0.1) | |||
| Hematological | 14624 ( 0.8) | 2823 ( 0.6) | |||
| Metabolic | 170040 ( 8.9) | 15144 ( 3.1) | |||
| Muscoskeletal/Skin disease | 26906 ( 1.4) | 6003 ( 1.2) | |||
| Neurological | 278905 ( 14.6) | 24108 ( 5.0) | |||
| Renal/Genitourinary | 45496 ( 2.4) | 12549 ( 2.6) | |||
| Respiratory | 236310 ( 12.4) | 116604 ( 24.0) | |||
| Sepsis | 52258 ( 2.7) | 218627 ( 45.1) | |||
| Trauma | 102234 ( 5.4) | 3019 ( 0.6) | |||
| Undefined | 17802 ( 0.9) | 1838 ( 0.4) | |||
| NA | 6483 ( 0.3) | 81 ( 0.0) |
25 Table 1 ALL After Inclusion/Exclusion
varsTable1 <- c("age", "gender2", "ethnicity2", "BMI_Ranges", "icu_admit_source2","physicianSpeciality2", "hospitaldischargeyear", "hospital_teaching_status", "hospital_size", "hospital_region2","dialysis", "aids", "hepaticfailure", "diabetes", "immunosuppression", "leukemia", "lymphoma", "metastaticcancer", "thrombolytics", "sofa_respiration_baseline2", "cardiovascular_baseline","SIRS_Positive", "qSOFA_Positive", "SOFA_Positive", "SepsisFuzzyLogicPositive","apacheiva", "hospital_mortality_ultimate", "icu_mortality", "hospital_los", "icu_los", "sepsis_outcome","group")
library(dplyr); library(Hmisc); library(ggplot2); library(sjPlot)
if(!("tableone" %in% rownames(installed.packages()))) {
install.packages("tableone")
}
library(tableone)
CreateTableOne(data=ssd_incl ,vars=varsTable1,strata="hospital_mortality_ultimate",test=TRUE, includeNA=TRUE
) %>% print(nonnormal= c("icu_mortality", "sepsis_outcome","hospital_teaching_status"),minMax=TRUE,
printToggle = FALSE,
showAllLevels = TRUE,
cramVars = "kon"
) %>%
{data.frame(
variable_name = gsub(" ", " ", rownames(.), fixed = TRUE), .,
row.names = NULL,
check.names = FALSE,
stringsAsFactors = FALSE)} %>%
knitr::kable(caption="Demographic, Severity of Illness, Diagnostic, and Outcome Data")| variable_name | level | 0 | 1 | p | test |
|---|---|---|---|---|---|
| n | 826290 | 86219 | |||
| age (mean (sd)) | 62.26 (17.20) | 69.51 (15.00) | <0.001 | ||
| gender2 (%) | Male | 444766 ( 53.8) | 45767 ( 53.1) | <0.001 | |
| Female | 381402 ( 46.2) | 40346 ( 46.8) | |||
| Other/Unknown | 122 ( 0.0) | 106 ( 0.1) | |||
| ethnicity2 (%) | Caucasian | 629231 ( 76.2) | 66136 ( 76.7) | <0.001 | |
| African American | 96168 ( 11.6) | 9124 ( 10.6) | |||
| Hispanic | 37359 ( 4.5) | 4034 ( 4.7) | |||
| Asian | 10468 ( 1.3) | 1227 ( 1.4) | |||
| Native American | 6085 ( 0.7) | 680 ( 0.8) | |||
| Other/Unknown | 46979 ( 5.7) | 5018 ( 5.8) | |||
| BMI_Ranges (%) | (0,18.5] | 37672 ( 4.6) | 6337 ( 7.3) | <0.001 | |
| (18.5,25] | 230063 ( 27.8) | 27575 ( 32.0) | |||
| (25,35] | 381728 ( 46.2) | 34794 ( 40.4) | |||
| (35,200] | 148643 ( 18.0) | 13411 ( 15.6) | |||
| Other/Unknown | 28184 ( 3.4) | 4102 ( 4.8) | |||
| icu_admit_source2 (%) | Floor | 131068 ( 15.9) | 23568 ( 27.3) | <0.001 | |
| OR/Proc Area | 169828 ( 20.6) | 6615 ( 7.7) | |||
| Direct Admit | 87805 ( 10.6) | 10233 ( 11.9) | |||
| Emergency Department | 415282 ( 50.3) | 41193 ( 47.8) | |||
| Other | 6616 ( 0.8) | 1147 ( 1.3) | |||
| Step-Down Unit | 15691 ( 1.9) | 3463 ( 4.0) | |||
| physicianSpeciality2 (%) | Critical Care | 235008 ( 28.4) | 32228 ( 37.4) | <0.001 | |
| Speciality-Other | 591282 ( 71.6) | 53991 ( 62.6) | |||
| hospitaldischargeyear (%) | -2010 | 100104 ( 12.1) | 11426 ( 13.3) | <0.001 | |
| 2011 | 109790 ( 13.3) | 12246 ( 14.2) | |||
| 2012 | 134912 ( 16.3) | 14257 ( 16.5) | |||
| 2013 | 151717 ( 18.4) | 15581 ( 18.1) | |||
| 2014 | 162398 ( 19.7) | 15789 ( 18.3) | |||
| 2015-16 | 167369 ( 20.3) | 16920 ( 19.6) | |||
| hospital_teaching_status (%) | 34473 ( 4.2) | 3442 ( 4.0) | <0.001 | ||
| f | 543349 ( 65.8) | 54693 ( 63.4) | |||
| t | 248468 ( 30.1) | 28084 ( 32.6) | |||
| hospital_size (%) | 66107 ( 8.0) | 6571 ( 7.6) | <0.001 | ||
| <100 | 34747 ( 4.2) | 2025 ( 2.3) | |||
| 100-249 | 190062 ( 23.0) | 17055 ( 19.8) | |||
| 250-500 | 151081 ( 18.3) | 16032 ( 18.6) | |||
| >500 | 384293 ( 46.5) | 44536 ( 51.7) | |||
| hospital_region2 (%) | Midwest | 352325 ( 42.6) | 30750 ( 35.7) | <0.001 | |
| Northeast | 63922 ( 7.7) | 9601 ( 11.1) | |||
| South | 256647 ( 31.1) | 27340 ( 31.7) | |||
| West | 102962 ( 12.5) | 13821 ( 16.0) | |||
| Unknown | 50434 ( 6.1) | 4707 ( 5.5) | |||
| dialysis (%) | 0 | 799492 ( 96.8) | 82383 ( 95.6) | <0.001 | |
| 1 | 26798 ( 3.2) | 3836 ( 4.4) | |||
| aids (%) | 0 | 825524 ( 99.9) | 86095 ( 99.9) | <0.001 | |
| 1 | 766 ( 0.1) | 124 ( 0.1) | |||
| hepaticfailure (%) | FALSE | 810457 ( 98.1) | 82987 ( 96.3) | <0.001 | |
| TRUE | 15833 ( 1.9) | 3232 ( 3.7) | |||
| diabetes (%) | 0 | 642502 ( 77.8) | 70191 ( 81.4) | <0.001 | |
| 1 | 183788 ( 22.2) | 16028 ( 18.6) | |||
| immunosuppression (%) | 0 | 808507 ( 97.8) | 82621 ( 95.8) | <0.001 | |
| 1 | 17783 ( 2.2) | 3598 ( 4.2) | |||
| leukemia (%) | 0 | 820977 ( 99.4) | 84948 ( 98.5) | <0.001 | |
| 1 | 5313 ( 0.6) | 1271 ( 1.5) | |||
| lymphoma (%) | 0 | 823248 ( 99.6) | 85647 ( 99.3) | <0.001 | |
| 1 | 3042 ( 0.4) | 572 ( 0.7) | |||
| metastaticcancer (%) | 0 | 812021 ( 98.3) | 82981 ( 96.2) | <0.001 | |
| 1 | 14269 ( 1.7) | 3238 ( 3.8) | |||
| thrombolytics (%) | 0 | 810938 ( 98.1) | 84836 ( 98.4) | <0.001 | |
| 1 | 15352 ( 1.9) | 1383 ( 1.6) | |||
| sofa_respiration_baseline2 (%) | FALSE | 630876 ( 76.4) | 61776 ( 71.7) | <0.001 | |
| TRUE | 195414 ( 23.6) | 24443 ( 28.3) | |||
| cardiovascular_baseline (%) | 0 | 642985 ( 77.8) | 62318 ( 72.3) | <0.001 | |
| 1 | 183305 ( 22.2) | 23901 ( 27.7) | |||
| SIRS_Positive (%) | FALSE | 212707 ( 25.7) | 5948 ( 6.9) | <0.001 | |
| TRUE | 613583 ( 74.3) | 80271 ( 93.1) | |||
| qSOFA_Positive (%) | FALSE | 291347 ( 35.3) | 8146 ( 9.4) | <0.001 | |
| TRUE | 534943 ( 64.7) | 78073 ( 90.6) | |||
| SOFA_Positive (%) | FALSE | 279544 ( 33.8) | 4749 ( 5.5) | <0.001 | |
| TRUE | 546746 ( 66.2) | 81470 ( 94.5) | |||
| SepsisFuzzyLogicPositive (%) | FALSE | 398466 ( 48.2) | 11535 ( 13.4) | <0.001 | |
| TRUE | 427824 ( 51.8) | 74684 ( 86.6) | |||
| apacheiva (mean (sd)) | 51.90 (22.17) | 90.36 (31.77) | <0.001 | ||
| hospital_mortality_ultimate (%) | 0 | 826290 (100.0) | 0 ( 0.0) | <0.001 | |
| 1 | 0 ( 0.0) | 86219 (100.0) | |||
| icu_mortality (%) | 0 | 826246 (100.0) | 24853 ( 28.8) | <0.001 | |
| 1 | 0 ( 0.0) | 61357 ( 71.2) | |||
| NA | 44 ( 0.0) | 9 ( 0.0) | |||
| hospital_los (mean (sd)) | 7.69 (9.37) | 7.97 (11.80) | <0.001 | ||
| icu_los (mean (sd)) | 2.93 (3.85) | 4.49 (5.84) | <0.001 | ||
| sepsis_outcome (%) | FALSE | 674037 ( 81.6) | 51602 ( 59.8) | <0.001 | |
| TRUE | 152253 ( 18.4) | 34617 ( 40.2) | |||
| group (%) | Cardiovascular | 270546 ( 32.7) | 24802 ( 28.8) | <0.001 | |
| Gastrointestinal | 87106 ( 10.5) | 7567 ( 8.8) | |||
| Gynaecological | 2381 ( 0.3) | 29 ( 0.0) | |||
| Hematological | 6220 ( 0.8) | 599 ( 0.7) | |||
| Metabolic | 73481 ( 8.9) | 1384 ( 1.6) | |||
| Muscoskeletal/Skin disease | 10969 ( 1.3) | 486 ( 0.6) | |||
| Neurological | 111809 ( 13.5) | 11101 ( 12.9) | |||
| Renal/Genitourinary | 20549 ( 2.5) | 1576 ( 1.8) | |||
| Respiratory | 118873 ( 14.4) | 17182 ( 19.9) | |||
| Sepsis | 79999 ( 9.7) | 17599 ( 20.4) | |||
| Trauma | 37405 ( 4.5) | 3090 ( 3.6) | |||
| Undefined | 6952 ( 0.8) | 804 ( 0.9) |
CreateTableOne(data=ssd_incl ,vars=varsTable1,strata="sepsis_outcome",test=TRUE, includeNA=TRUE
) %>% print(nonnormal= c("hospital_mortality_ultimate", "icu_mortality", "hospital_teaching_status"),minMax=TRUE,
printToggle = FALSE,
showAllLevels = TRUE,
cramVars = "kon"
) %>%
{data.frame(
variable_name = gsub(" ", " ", rownames(.), fixed = TRUE), .,
row.names = NULL,
check.names = FALSE,
stringsAsFactors = FALSE)} %>%
knitr::kable(caption="Demographic, Severity of Illness, Diagnostic, and Outcome Data")| variable_name | level | FALSE | TRUE | p | test |
|---|---|---|---|---|---|
| n | 725639 | 186870 | |||
| age (mean (sd)) | 62.23 (17.30) | 65.70 (16.18) | <0.001 | ||
| gender2 (%) | Male | 395985 ( 54.6) | 94548 ( 50.6) | <0.001 | |
| Female | 329455 ( 45.4) | 92293 ( 49.4) | |||
| Other/Unknown | 199 ( 0.0) | 29 ( 0.0) | |||
| ethnicity2 (%) | Caucasian | 553821 ( 76.3) | 141546 ( 75.7) | <0.001 | |
| African American | 84902 ( 11.7) | 20390 ( 10.9) | |||
| Hispanic | 30536 ( 4.2) | 10857 ( 5.8) | |||
| Asian | 9221 ( 1.3) | 2474 ( 1.3) | |||
| Native American | 5248 ( 0.7) | 1517 ( 0.8) | |||
| Other/Unknown | 41911 ( 5.8) | 10086 ( 5.4) | |||
| BMI_Ranges (%) | (0,18.5] | 31764 ( 4.4) | 12245 ( 6.6) | <0.001 | |
| (18.5,25] | 202170 ( 27.9) | 55468 ( 29.7) | |||
| (25,35] | 338933 ( 46.7) | 77589 ( 41.5) | |||
| (35,200] | 125888 ( 17.3) | 36166 ( 19.4) | |||
| Other/Unknown | 26884 ( 3.7) | 5402 ( 2.9) | |||
| icu_admit_source2 (%) | Floor | 107913 ( 14.9) | 46723 ( 25.0) | <0.001 | |
| OR/Proc Area | 166553 ( 23.0) | 9890 ( 5.3) | |||
| Direct Admit | 80562 ( 11.1) | 17476 ( 9.4) | |||
| Emergency Department | 351730 ( 48.5) | 104745 ( 56.1) | |||
| Other | 5693 ( 0.8) | 2070 ( 1.1) | |||
| Step-Down Unit | 13188 ( 1.8) | 5966 ( 3.2) | |||
| physicianSpeciality2 (%) | Critical Care | 194821 ( 26.8) | 72415 ( 38.8) | <0.001 | |
| Speciality-Other | 530818 ( 73.2) | 114455 ( 61.2) | |||
| hospitaldischargeyear (%) | -2010 | 88588 ( 12.2) | 22942 ( 12.3) | <0.001 | |
| 2011 | 95007 ( 13.1) | 27029 ( 14.5) | |||
| 2012 | 119084 ( 16.4) | 30085 ( 16.1) | |||
| 2013 | 133576 ( 18.4) | 33722 ( 18.0) | |||
| 2014 | 142947 ( 19.7) | 35240 ( 18.9) | |||
| 2015-16 | 146437 ( 20.2) | 37852 ( 20.3) | |||
| hospital_teaching_status (%) | 30704 ( 4.2) | 7211 ( 3.9) | <0.001 | ||
| f | 476998 ( 65.7) | 121044 ( 64.8) | |||
| t | 217937 ( 30.0) | 58615 ( 31.4) | |||
| hospital_size (%) | 58989 ( 8.1) | 13689 ( 7.3) | <0.001 | ||
| <100 | 26993 ( 3.7) | 9779 ( 5.2) | |||
| 100-249 | 163833 ( 22.6) | 43284 ( 23.2) | |||
| 250-500 | 131717 ( 18.2) | 35396 ( 18.9) | |||
| >500 | 344107 ( 47.4) | 84722 ( 45.3) | |||
| hospital_region2 (%) | Midwest | 313401 ( 43.2) | 69674 ( 37.3) | <0.001 | |
| Northeast | 46163 ( 6.4) | 27360 ( 14.6) | |||
| South | 229437 ( 31.6) | 54550 ( 29.2) | |||
| West | 90846 ( 12.5) | 25937 ( 13.9) | |||
| Unknown | 45792 ( 6.3) | 9349 ( 5.0) | |||
| dialysis (%) | 0 | 702756 ( 96.8) | 179119 ( 95.9) | <0.001 | |
| 1 | 22883 ( 3.2) | 7751 ( 4.1) | |||
| aids (%) | 0 | 725221 ( 99.9) | 186398 ( 99.7) | <0.001 | |
| 1 | 418 ( 0.1) | 472 ( 0.3) | |||
| hepaticfailure (%) | FALSE | 711408 ( 98.0) | 182036 ( 97.4) | <0.001 | |
| TRUE | 14231 ( 2.0) | 4834 ( 2.6) | |||
| diabetes (%) | 0 | 566573 ( 78.1) | 146120 ( 78.2) | 0.288 | |
| 1 | 159066 ( 21.9) | 40750 ( 21.8) | |||
| immunosuppression (%) | 0 | 711733 ( 98.1) | 179395 ( 96.0) | <0.001 | |
| 1 | 13906 ( 1.9) | 7475 ( 4.0) | |||
| leukemia (%) | 0 | 721482 ( 99.4) | 184443 ( 98.7) | <0.001 | |
| 1 | 4157 ( 0.6) | 2427 ( 1.3) | |||
| lymphoma (%) | 0 | 723226 ( 99.7) | 185669 ( 99.4) | <0.001 | |
| 1 | 2413 ( 0.3) | 1201 ( 0.6) | |||
| metastaticcancer (%) | 0 | 712655 ( 98.2) | 182347 ( 97.6) | <0.001 | |
| 1 | 12984 ( 1.8) | 4523 ( 2.4) | |||
| thrombolytics (%) | 0 | 709288 ( 97.7) | 186486 ( 99.8) | <0.001 | |
| 1 | 16351 ( 2.3) | 384 ( 0.2) | |||
| sofa_respiration_baseline2 (%) | FALSE | 569370 ( 78.5) | 123282 ( 66.0) | <0.001 | |
| TRUE | 156269 ( 21.5) | 63588 ( 34.0) | |||
| cardiovascular_baseline (%) | 0 | 564204 ( 77.8) | 141099 ( 75.5) | <0.001 | |
| 1 | 161435 ( 22.2) | 45771 ( 24.5) | |||
| SIRS_Positive (%) | FALSE | 197738 ( 27.3) | 20917 ( 11.2) | <0.001 | |
| TRUE | 527901 ( 72.7) | 165953 ( 88.8) | |||
| qSOFA_Positive (%) | FALSE | 265487 ( 36.6) | 34006 ( 18.2) | <0.001 | |
| TRUE | 460152 ( 63.4) | 152864 ( 81.8) | |||
| SOFA_Positive (%) | FALSE | 258188 ( 35.6) | 26105 ( 14.0) | <0.001 | |
| TRUE | 467451 ( 64.4) | 160765 ( 86.0) | |||
| SepsisFuzzyLogicPositive (%) | FALSE | 375201 ( 51.7) | 34800 ( 18.6) | <0.001 | |
| TRUE | 350438 ( 48.3) | 152070 ( 81.4) | |||
| apacheiva (mean (sd)) | 51.95 (23.95) | 69.47 (28.02) | <0.001 | ||
| hospital_mortality_ultimate (%) | 0 | 674037 ( 92.9) | 152253 ( 81.5) | <0.001 | |
| 1 | 51602 ( 7.1) | 34617 ( 18.5) | |||
| icu_mortality (%) | 0 | 689161 ( 95.0) | 161938 ( 86.7) | <0.001 | |
| 1 | 36436 ( 5.0) | 24921 ( 13.3) | |||
| NA | 42 ( 0.0) | 11 ( 0.0) | |||
| hospital_los (mean (sd)) | 7.05 (8.71) | 10.31 (12.24) | <0.001 | ||
| icu_los (mean (sd)) | 2.79 (3.75) | 4.20 (5.13) | <0.001 | ||
| sepsis_outcome (%) | FALSE | 725639 (100.0) | 0 ( 0.0) | <0.001 | |
| TRUE | 0 ( 0.0) | 186870 (100.0) | |||
| group (%) | Cardiovascular | 275329 ( 37.9) | 20019 ( 10.7) | <0.001 | |
| Gastrointestinal | 83127 ( 11.5) | 11546 ( 6.2) | |||
| Gynaecological | 2293 ( 0.3) | 117 ( 0.1) | |||
| Hematological | 5761 ( 0.8) | 1058 ( 0.6) | |||
| Metabolic | 68815 ( 9.5) | 6050 ( 3.2) | |||
| Muscoskeletal/Skin disease | 9185 ( 1.3) | 2270 ( 1.2) | |||
| Neurological | 113662 ( 15.7) | 9248 ( 4.9) | |||
| Renal/Genitourinary | 17170 ( 2.4) | 4955 ( 2.7) | |||
| Respiratory | 89707 ( 12.4) | 46348 ( 24.8) | |||
| Sepsis | 14033 ( 1.9) | 83565 ( 44.7) | |||
| Trauma | 39475 ( 5.4) | 1020 ( 0.5) | |||
| Undefined | 7082 ( 1.0) | 674 ( 0.4) |
26 Table 1 Test Dataset
varsTable1 <- c("age", "gender2", "ethnicity2", "BMI_Ranges", "icu_admit_source2","physicianSpeciality2", "hospitaldischargeyear", "hospital_teaching_status", "hospital_size", "hospital_region2","dialysis", "aids", "hepaticfailure", "diabetes", "immunosuppression", "leukemia", "lymphoma", "metastaticcancer", "thrombolytics", "sofa_respiration_baseline2", "cardiovascular_baseline","SIRS_Positive", "qSOFA_Positive", "SOFA_Positive", "SepsisFuzzyLogicPositive","apacheiva", "hospital_mortality_ultimate", "icu_mortality", "hospital_los", "icu_los","sepsis_outcome", "group")
library(dplyr); library(Hmisc); library(ggplot2); library(sjPlot)
if(!("tableone" %in% rownames(installed.packages()))) {
install.packages("tableone")
}
library(tableone)
CreateTableOne(data=ssd_incl_te ,vars=varsTable1,strata="hospital_mortality_ultimate",test=TRUE, includeNA=TRUE
) %>% print(nonnormal= c("icu_mortality", "sepsis_outcome","hospital_teaching_status"),minMax=TRUE,
printToggle = FALSE,
showAllLevels = TRUE,
cramVars = "kon"
) %>%
{data.frame(
variable_name = gsub(" ", " ", rownames(.), fixed = TRUE), .,
row.names = NULL,
check.names = FALSE,
stringsAsFactors = FALSE)} %>%
knitr::kable(caption="Demographic, Severity of Illness, Diagnostic, and Outcome Data")| variable_name | level | FALSE | TRUE | p | test |
|---|---|---|---|---|---|
| n | 247887 | 25865 | |||
| age (mean (sd)) | 62.23 (17.23) | 69.63 (14.92) | <0.001 | ||
| gender2 (%) | Male | 133288 ( 53.8) | 13614 ( 52.6) | <0.001 | |
| Female | 114558 ( 46.2) | 12212 ( 47.2) | |||
| Other/Unknown | 41 ( 0.0) | 39 ( 0.2) | |||
| ethnicity2 (%) | Caucasian | 188789 ( 76.2) | 19899 ( 76.9) | <0.001 | |
| African American | 28950 ( 11.7) | 2779 ( 10.7) | |||
| Hispanic | 11097 ( 4.5) | 1188 ( 4.6) | |||
| Asian | 3171 ( 1.3) | 362 ( 1.4) | |||
| Native American | 1834 ( 0.7) | 178 ( 0.7) | |||
| Other/Unknown | 14046 ( 5.7) | 1459 ( 5.6) | |||
| BMI_Ranges (%) | (0,18.5] | 11536 ( 4.7) | 1912 ( 7.4) | <0.001 | |
| (18.5,25] | 68576 ( 27.7) | 8299 ( 32.1) | |||
| (25,35] | 114763 ( 46.3) | 10449 ( 40.4) | |||
| (35,200] | 44499 ( 18.0) | 3958 ( 15.3) | |||
| Other/Unknown | 8513 ( 3.4) | 1247 ( 4.8) | |||
| icu_admit_source2 (%) | Floor | 39313 ( 15.9) | 7121 ( 27.5) | <0.001 | |
| OR/Proc Area | 50962 ( 20.6) | 1969 ( 7.6) | |||
| Direct Admit | 26416 ( 10.7) | 3055 ( 11.8) | |||
| Emergency Department | 124404 ( 50.2) | 12270 ( 47.4) | |||
| Other | 1995 ( 0.8) | 365 ( 1.4) | |||
| Step-Down Unit | 4797 ( 1.9) | 1085 ( 4.2) | |||
| physicianSpeciality2 (%) | Critical Care | 70540 ( 28.5) | 9755 ( 37.7) | <0.001 | |
| Speciality-Other | 177347 ( 71.5) | 16110 ( 62.3) | |||
| hospitaldischargeyear (%) | -2010 | 29982 ( 12.1) | 3366 ( 13.0) | <0.001 | |
| 2011 | 33134 ( 13.4) | 3680 ( 14.2) | |||
| 2012 | 40551 ( 16.4) | 4259 ( 16.5) | |||
| 2013 | 45509 ( 18.4) | 4753 ( 18.4) | |||
| 2014 | 48843 ( 19.7) | 4708 ( 18.2) | |||
| 2015-16 | 49868 ( 20.1) | 5099 ( 19.7) | |||
| hospital_teaching_status (%) | 10370 ( 4.2) | 1051 ( 4.1) | <0.001 | ||
| f | 162894 ( 65.7) | 16377 ( 63.3) | |||
| t | 74623 ( 30.1) | 8437 ( 32.6) | |||
| hospital_size (%) | 19895 ( 8.0) | 1985 ( 7.7) | <0.001 | ||
| <100 | 10464 ( 4.2) | 614 ( 2.4) | |||
| 100-249 | 56948 ( 23.0) | 5071 ( 19.6) | |||
| 250-500 | 45347 ( 18.3) | 4859 ( 18.8) | |||
| >500 | 115233 ( 46.5) | 13336 ( 51.6) | |||
| hospital_region2 (%) | Midwest | 105735 ( 42.7) | 9171 ( 35.5) | <0.001 | |
| Northeast | 19043 ( 7.7) | 2962 ( 11.5) | |||
| South | 77072 ( 31.1) | 8209 ( 31.7) | |||
| West | 30786 ( 12.4) | 4083 ( 15.8) | |||
| Unknown | 15251 ( 6.2) | 1440 ( 5.6) | |||
| dialysis (%) | 0 | 239806 ( 96.7) | 24688 ( 95.4) | <0.001 | |
| 1 | 8081 ( 3.3) | 1177 ( 4.6) | |||
| aids (%) | 0 | 247657 ( 99.9) | 25832 ( 99.9) | 0.107 | |
| 1 | 230 ( 0.1) | 33 ( 0.1) | |||
| hepaticfailure (%) | FALSE | 243163 ( 98.1) | 24908 ( 96.3) | <0.001 | |
| TRUE | 4724 ( 1.9) | 957 ( 3.7) | |||
| diabetes (%) | 0 | 192864 ( 77.8) | 21056 ( 81.4) | <0.001 | |
| 1 | 55023 ( 22.2) | 4809 ( 18.6) | |||
| immunosuppression (%) | 0 | 242591 ( 97.9) | 24795 ( 95.9) | <0.001 | |
| 1 | 5296 ( 2.1) | 1070 ( 4.1) | |||
| leukemia (%) | 0 | 246333 ( 99.4) | 25481 ( 98.5) | <0.001 | |
| 1 | 1554 ( 0.6) | 384 ( 1.5) | |||
| lymphoma (%) | 0 | 247024 ( 99.7) | 25698 ( 99.4) | <0.001 | |
| 1 | 863 ( 0.3) | 167 ( 0.6) | |||
| metastaticcancer (%) | 0 | 243535 ( 98.2) | 24911 ( 96.3) | <0.001 | |
| 1 | 4352 ( 1.8) | 954 ( 3.7) | |||
| thrombolytics (%) | 0 | 243323 ( 98.2) | 25461 ( 98.4) | 0.001 | |
| 1 | 4564 ( 1.8) | 404 ( 1.6) | |||
| sofa_respiration_baseline2 (%) | FALSE | 189447 ( 76.4) | 18561 ( 71.8) | <0.001 | |
| TRUE | 58440 ( 23.6) | 7304 ( 28.2) | |||
| cardiovascular_baseline (%) | 0 | 193108 ( 77.9) | 18753 ( 72.5) | <0.001 | |
| 1 | 54779 ( 22.1) | 7112 ( 27.5) | |||
| SIRS_Positive (%) | FALSE | 63427 ( 25.6) | 1792 ( 6.9) | <0.001 | |
| TRUE | 184460 ( 74.4) | 24073 ( 93.1) | |||
| qSOFA_Positive (%) | FALSE | 87257 ( 35.2) | 2429 ( 9.4) | <0.001 | |
| TRUE | 160630 ( 64.8) | 23436 ( 90.6) | |||
| SOFA_Positive (%) | FALSE | 83807 ( 33.8) | 1464 ( 5.7) | <0.001 | |
| TRUE | 164080 ( 66.2) | 24401 ( 94.3) | |||
| SepsisFuzzyLogicPositive (%) | FALSE | 119438 ( 48.2) | 3492 ( 13.5) | <0.001 | |
| TRUE | 128449 ( 51.8) | 22373 ( 86.5) | |||
| apacheiva (mean (sd)) | 51.90 (22.21) | 90.36 (31.62) | <0.001 | ||
| hospital_mortality_ultimate (%) | FALSE | 247887 (100.0) | 0 ( 0.0) | <0.001 | |
| TRUE | 0 ( 0.0) | 25865 (100.0) | |||
| icu_mortality (%) | 0 | 247870 (100.0) | 7507 ( 29.0) | <0.001 | |
| 1 | 0 ( 0.0) | 18355 ( 71.0) | |||
| NA | 17 ( 0.0) | 3 ( 0.0) | |||
| hospital_los (mean (sd)) | 7.74 (10.56) | 7.96 (10.32) | 0.001 | ||
| icu_los (mean (sd)) | 2.94 (3.90) | 4.46 (5.87) | <0.001 | ||
| sepsis_outcome (%) | FALSE | 202080 ( 81.5) | 15416 ( 59.6) | <0.001 | |
| TRUE | 45807 ( 18.5) | 10449 ( 40.4) | |||
| group (%) | Cardiovascular | 80965 ( 32.7) | 7398 ( 28.6) | <0.001 | |
| Gastrointestinal | 26265 ( 10.6) | 2279 ( 8.8) | |||
| Gynaecological | 706 ( 0.3) | 9 ( 0.0) | |||
| Hematological | 1915 ( 0.8) | 171 ( 0.7) | |||
| Metabolic | 22029 ( 8.9) | 432 ( 1.7) | |||
| Muscoskeletal/Skin disease | 3332 ( 1.3) | 126 ( 0.5) | |||
| Neurological | 33500 ( 13.5) | 3337 ( 12.9) | |||
| Renal/Genitourinary | 6101 ( 2.5) | 475 ( 1.8) | |||
| Respiratory | 35716 ( 14.4) | 5142 ( 19.9) | |||
| Sepsis | 24033 ( 9.7) | 5304 ( 20.5) | |||
| Trauma | 11196 ( 4.5) | 929 ( 3.6) | |||
| Undefined | 2129 ( 0.9) | 263 ( 1.0) |
CreateTableOne(data=ssd_incl_te ,vars=varsTable1,strata="sepsis_outcome",test=TRUE, includeNA=TRUE
) %>% print(nonnormal= c("hospital_mortality_ultimate", "icu_mortality", "hospital_teaching_status"),minMax=TRUE,
printToggle = FALSE,
showAllLevels = TRUE,
cramVars = "kon"
) %>%
{data.frame(
variable_name = gsub(" ", " ", rownames(.), fixed = TRUE), .,
row.names = NULL,
check.names = FALSE,
stringsAsFactors = FALSE)} %>%
knitr::kable(caption="Demographic, Severity of Illness, Diagnostic, and Outcome Data")| variable_name | level | FALSE | TRUE | p | test |
|---|---|---|---|---|---|
| n | 217496 | 56256 | |||
| age (mean (sd)) | 62.21 (17.32) | 65.70 (16.27) | <0.001 | ||
| gender2 (%) | Male | 118663 ( 54.6) | 28239 ( 50.2) | <0.001 | |
| Female | 98765 ( 45.4) | 28005 ( 49.8) | |||
| Other/Unknown | 68 ( 0.0) | 12 ( 0.0) | |||
| ethnicity2 (%) | Caucasian | 166045 ( 76.3) | 42643 ( 75.8) | <0.001 | |
| African American | 25606 ( 11.8) | 6123 ( 10.9) | |||
| Hispanic | 9025 ( 4.1) | 3260 ( 5.8) | |||
| Asian | 2785 ( 1.3) | 748 ( 1.3) | |||
| Native American | 1558 ( 0.7) | 454 ( 0.8) | |||
| Other/Unknown | 12477 ( 5.7) | 3028 ( 5.4) | |||
| BMI_Ranges (%) | (0,18.5] | 9746 ( 4.5) | 3702 ( 6.6) | <0.001 | |
| (18.5,25] | 60170 ( 27.7) | 16705 ( 29.7) | |||
| (25,35] | 101869 ( 46.8) | 23343 ( 41.5) | |||
| (35,200] | 37638 ( 17.3) | 10819 ( 19.2) | |||
| Other/Unknown | 8073 ( 3.7) | 1687 ( 3.0) | |||
| icu_admit_source2 (%) | Floor | 32429 ( 14.9) | 14005 ( 24.9) | <0.001 | |
| OR/Proc Area | 49937 ( 23.0) | 2994 ( 5.3) | |||
| Direct Admit | 24281 ( 11.2) | 5190 ( 9.2) | |||
| Emergency Department | 105092 ( 48.3) | 31582 ( 56.1) | |||
| Other | 1722 ( 0.8) | 638 ( 1.1) | |||
| Step-Down Unit | 4035 ( 1.9) | 1847 ( 3.3) | |||
| physicianSpeciality2 (%) | Critical Care | 58418 ( 26.9) | 21877 ( 38.9) | <0.001 | |
| Speciality-Other | 159078 ( 73.1) | 34379 ( 61.1) | |||
| hospitaldischargeyear (%) | -2010 | 26447 ( 12.2) | 6901 ( 12.3) | <0.001 | |
| 2011 | 28696 ( 13.2) | 8118 ( 14.4) | |||
| 2012 | 35707 ( 16.4) | 9103 ( 16.2) | |||
| 2013 | 40113 ( 18.4) | 10149 ( 18.0) | |||
| 2014 | 42963 ( 19.8) | 10588 ( 18.8) | |||
| 2015-16 | 43570 ( 20.0) | 11397 ( 20.3) | |||
| hospital_teaching_status (%) | 9199 ( 4.2) | 2222 ( 3.9) | <0.001 | ||
| f | 143044 ( 65.8) | 36227 ( 64.4) | |||
| t | 65253 ( 30.0) | 17807 ( 31.7) | |||
| hospital_size (%) | 17716 ( 8.1) | 4164 ( 7.4) | <0.001 | ||
| <100 | 8157 ( 3.8) | 2921 ( 5.2) | |||
| 100-249 | 48999 ( 22.5) | 13020 ( 23.1) | |||
| 250-500 | 39608 ( 18.2) | 10598 ( 18.8) | |||
| >500 | 103016 ( 47.4) | 25553 ( 45.4) | |||
| hospital_region2 (%) | Midwest | 93946 ( 43.2) | 20960 ( 37.3) | <0.001 | |
| Northeast | 13710 ( 6.3) | 8295 ( 14.7) | |||
| South | 68820 ( 31.6) | 16461 ( 29.3) | |||
| West | 27201 ( 12.5) | 7668 ( 13.6) | |||
| Unknown | 13819 ( 6.4) | 2872 ( 5.1) | |||
| dialysis (%) | 0 | 210546 ( 96.8) | 53948 ( 95.9) | <0.001 | |
| 1 | 6950 ( 3.2) | 2308 ( 4.1) | |||
| aids (%) | 0 | 217391 (100.0) | 56098 ( 99.7) | <0.001 | |
| 1 | 105 ( 0.0) | 158 ( 0.3) | |||
| hepaticfailure (%) | FALSE | 213245 ( 98.0) | 54826 ( 97.5) | <0.001 | |
| TRUE | 4251 ( 2.0) | 1430 ( 2.5) | |||
| diabetes (%) | 0 | 169968 ( 78.1) | 43952 ( 78.1) | 0.927 | |
| 1 | 47528 ( 21.9) | 12304 ( 21.9) | |||
| immunosuppression (%) | 0 | 213347 ( 98.1) | 54039 ( 96.1) | <0.001 | |
| 1 | 4149 ( 1.9) | 2217 ( 3.9) | |||
| leukemia (%) | 0 | 216306 ( 99.5) | 55508 ( 98.7) | <0.001 | |
| 1 | 1190 ( 0.5) | 748 ( 1.3) | |||
| lymphoma (%) | 0 | 216810 ( 99.7) | 55912 ( 99.4) | <0.001 | |
| 1 | 686 ( 0.3) | 344 ( 0.6) | |||
| metastaticcancer (%) | 0 | 213552 ( 98.2) | 54894 ( 97.6) | <0.001 | |
| 1 | 3944 ( 1.8) | 1362 ( 2.4) | |||
| thrombolytics (%) | 0 | 212624 ( 97.8) | 56160 ( 99.8) | <0.001 | |
| 1 | 4872 ( 2.2) | 96 ( 0.2) | |||
| sofa_respiration_baseline2 (%) | FALSE | 170825 ( 78.5) | 37183 ( 66.1) | <0.001 | |
| TRUE | 46671 ( 21.5) | 19073 ( 33.9) | |||
| cardiovascular_baseline (%) | 0 | 169312 ( 77.8) | 42549 ( 75.6) | <0.001 | |
| 1 | 48184 ( 22.2) | 13707 ( 24.4) | |||
| SIRS_Positive (%) | FALSE | 59019 ( 27.1) | 6200 ( 11.0) | <0.001 | |
| TRUE | 158477 ( 72.9) | 50056 ( 89.0) | |||
| qSOFA_Positive (%) | FALSE | 79553 ( 36.6) | 10133 ( 18.0) | <0.001 | |
| TRUE | 137943 ( 63.4) | 46123 ( 82.0) | |||
| SOFA_Positive (%) | FALSE | 77471 ( 35.6) | 7800 ( 13.9) | <0.001 | |
| TRUE | 140025 ( 64.4) | 48456 ( 86.1) | |||
| SepsisFuzzyLogicPositive (%) | FALSE | 112558 ( 51.8) | 10372 ( 18.4) | <0.001 | |
| TRUE | 104938 ( 48.2) | 45884 ( 81.6) | |||
| apacheiva (mean (sd)) | 51.93 (23.93) | 69.48 (28.13) | <0.001 | ||
| hospital_mortality_ultimate (%) | FALSE | 202080 ( 92.9) | 45807 ( 81.4) | <0.001 | |
| TRUE | 15416 ( 7.1) | 10449 ( 18.6) | |||
| icu_mortality (%) | 0 | 206618 ( 95.0) | 48759 ( 86.7) | <0.001 | |
| 1 | 10863 ( 5.0) | 7492 ( 13.3) | |||
| NA | 15 ( 0.0) | 5 ( 0.0) | |||
| hospital_los (mean (sd)) | 7.08 (9.34) | 10.38 (13.93) | <0.001 | ||
| icu_los (mean (sd)) | 2.79 (3.78) | 4.22 (5.20) | <0.001 | ||
| sepsis_outcome (%) | FALSE | 217496 (100.0) | 0 ( 0.0) | <0.001 | |
| TRUE | 0 ( 0.0) | 56256 (100.0) | |||
| group (%) | Cardiovascular | 82285 ( 37.8) | 6078 ( 10.8) | <0.001 | |
| Gastrointestinal | 25028 ( 11.5) | 3516 ( 6.2) | |||
| Gynaecological | 682 ( 0.3) | 33 ( 0.1) | |||
| Hematological | 1779 ( 0.8) | 307 ( 0.5) | |||
| Metabolic | 20612 ( 9.5) | 1849 ( 3.3) | |||
| Muscoskeletal/Skin disease | 2779 ( 1.3) | 679 ( 1.2) | |||
| Neurological | 34048 ( 15.7) | 2789 ( 5.0) | |||
| Renal/Genitourinary | 5089 ( 2.3) | 1487 ( 2.6) | |||
| Respiratory | 26953 ( 12.4) | 13905 ( 24.7) | |||
| Sepsis | 4250 ( 2.0) | 25087 ( 44.6) | |||
| Trauma | 11811 ( 5.4) | 314 ( 0.6) | |||
| Undefined | 2180 ( 1.0) | 212 ( 0.4) |
27 Table 1 Train Dataset
varsTable1 <- c("age", "gender2", "ethnicity2", "BMI_Ranges", "icu_admit_source2","physicianSpeciality2", "hospitaldischargeyear", "hospital_teaching_status", "hospital_size", "hospital_region2","dialysis", "aids", "hepaticfailure", "diabetes", "immunosuppression", "leukemia", "lymphoma", "metastaticcancer", "thrombolytics", "sofa_respiration_baseline2", "cardiovascular_baseline","SIRS_Positive", "qSOFA_Positive", "SOFA_Positive", "SepsisFuzzyLogicPositive","apacheiva", "hospital_mortality_ultimate", "icu_mortality", "hospital_los", "icu_los","sepsis_outcome","group")
library(dplyr); library(Hmisc); library(ggplot2); library(sjPlot)
if(!("tableone" %in% rownames(installed.packages()))) {
install.packages("tableone")
}
library(tableone)
CreateTableOne(data=ssd_incl_tr ,vars=varsTable1,strata="hospital_mortality_ultimate",test=TRUE, includeNA=TRUE
) %>% print(nonnormal= c("icu_mortality", "hospital_teaching_status"),minMax=TRUE,
printToggle = FALSE,
showAllLevels = TRUE,
cramVars = "kon"
) %>%
{data.frame(
variable_name = gsub(" ", " ", rownames(.), fixed = TRUE), .,
row.names = NULL,
check.names = FALSE,
stringsAsFactors = FALSE)} %>%
knitr::kable(caption="Demographic, Severity of Illness, Diagnostic, and Outcome Data")| variable_name | level | 0 | 1 | p | test |
|---|---|---|---|---|---|
| n | 578403 | 60354 | |||
| age (mean (sd)) | 62.27 (17.19) | 69.45 (15.04) | <0.001 | ||
| gender2 (%) | Male | 311478 ( 53.9) | 32153 ( 53.3) | <0.001 | |
| Female | 266844 ( 46.1) | 28134 ( 46.6) | |||
| Other/Unknown | 81 ( 0.0) | 67 ( 0.1) | |||
| ethnicity2 (%) | Caucasian | 440442 ( 76.1) | 46237 ( 76.6) | <0.001 | |
| African American | 67218 ( 11.6) | 6345 ( 10.5) | |||
| Hispanic | 26262 ( 4.5) | 2846 ( 4.7) | |||
| Asian | 7297 ( 1.3) | 865 ( 1.4) | |||
| Native American | 4251 ( 0.7) | 502 ( 0.8) | |||
| Other/Unknown | 32933 ( 5.7) | 3559 ( 5.9) | |||
| BMI_Ranges (%) | (0,18.5] | 26136 ( 4.5) | 4425 ( 7.3) | <0.001 | |
| (18.5,25] | 161487 ( 27.9) | 19276 ( 31.9) | |||
| (25,35] | 266965 ( 46.2) | 24345 ( 40.3) | |||
| (35,200] | 104144 ( 18.0) | 9453 ( 15.7) | |||
| Other/Unknown | 19671 ( 3.4) | 2855 ( 4.7) | |||
| icu_admit_source2 (%) | Floor | 91755 ( 15.9) | 16447 ( 27.3) | <0.001 | |
| OR/Proc Area | 118866 ( 20.6) | 4646 ( 7.7) | |||
| Direct Admit | 61389 ( 10.6) | 7178 ( 11.9) | |||
| Emergency Department | 290878 ( 50.3) | 28923 ( 47.9) | |||
| Other | 4621 ( 0.8) | 782 ( 1.3) | |||
| Step-Down Unit | 10894 ( 1.9) | 2378 ( 3.9) | |||
| physicianSpeciality2 (%) | Critical Care | 164468 ( 28.4) | 22473 ( 37.2) | <0.001 | |
| Speciality-Other | 413935 ( 71.6) | 37881 ( 62.8) | |||
| hospitaldischargeyear (%) | -2010 | 70122 ( 12.1) | 8060 ( 13.4) | <0.001 | |
| 2011 | 76656 ( 13.3) | 8566 ( 14.2) | |||
| 2012 | 94361 ( 16.3) | 9998 ( 16.6) | |||
| 2013 | 106208 ( 18.4) | 10828 ( 17.9) | |||
| 2014 | 113555 ( 19.6) | 11081 ( 18.4) | |||
| 2015-16 | 117501 ( 20.3) | 11821 ( 19.6) | |||
| hospital_teaching_status (%) | 24103 ( 4.2) | 2391 ( 4.0) | <0.001 | ||
| f | 380455 ( 65.8) | 38316 ( 63.5) | |||
| t | 173845 ( 30.1) | 19647 ( 32.6) | |||
| hospital_size (%) | 46212 ( 8.0) | 4586 ( 7.6) | <0.001 | ||
| <100 | 24283 ( 4.2) | 1411 ( 2.3) | |||
| 100-249 | 133114 ( 23.0) | 11984 ( 19.9) | |||
| 250-500 | 105734 ( 18.3) | 11173 ( 18.5) | |||
| >500 | 269060 ( 46.5) | 31200 ( 51.7) | |||
| hospital_region2 (%) | Midwest | 246590 ( 42.6) | 21579 ( 35.8) | <0.001 | |
| Northeast | 44879 ( 7.8) | 6639 ( 11.0) | |||
| South | 179575 ( 31.0) | 19131 ( 31.7) | |||
| West | 72176 ( 12.5) | 9738 ( 16.1) | |||
| Unknown | 35183 ( 6.1) | 3267 ( 5.4) | |||
| dialysis (%) | 0 | 559686 ( 96.8) | 57695 ( 95.6) | <0.001 | |
| 1 | 18717 ( 3.2) | 2659 ( 4.4) | |||
| aids (%) | 0 | 577867 ( 99.9) | 60263 ( 99.8) | <0.001 | |
| 1 | 536 ( 0.1) | 91 ( 0.2) | |||
| hepaticfailure (%) | FALSE | 567294 ( 98.1) | 58079 ( 96.2) | <0.001 | |
| TRUE | 11109 ( 1.9) | 2275 ( 3.8) | |||
| diabetes (%) | 0 | 449638 ( 77.7) | 49135 ( 81.4) | <0.001 | |
| 1 | 128765 ( 22.3) | 11219 ( 18.6) | |||
| immunosuppression (%) | 0 | 565916 ( 97.8) | 57826 ( 95.8) | <0.001 | |
| 1 | 12487 ( 2.2) | 2528 ( 4.2) | |||
| leukemia (%) | 0 | 574644 ( 99.4) | 59467 ( 98.5) | <0.001 | |
| 1 | 3759 ( 0.6) | 887 ( 1.5) | |||
| lymphoma (%) | 0 | 576224 ( 99.6) | 59949 ( 99.3) | <0.001 | |
| 1 | 2179 ( 0.4) | 405 ( 0.7) | |||
| metastaticcancer (%) | 0 | 568486 ( 98.3) | 58070 ( 96.2) | <0.001 | |
| 1 | 9917 ( 1.7) | 2284 ( 3.8) | |||
| thrombolytics (%) | 0 | 567615 ( 98.1) | 59375 ( 98.4) | <0.001 | |
| 1 | 10788 ( 1.9) | 979 ( 1.6) | |||
| sofa_respiration_baseline2 (%) | FALSE | 441429 ( 76.3) | 43215 ( 71.6) | <0.001 | |
| TRUE | 136974 ( 23.7) | 17139 ( 28.4) | |||
| cardiovascular_baseline (%) | 0 | 449877 ( 77.8) | 43565 ( 72.2) | <0.001 | |
| 1 | 128526 ( 22.2) | 16789 ( 27.8) | |||
| SIRS_Positive (%) | FALSE | 149280 ( 25.8) | 4156 ( 6.9) | <0.001 | |
| TRUE | 429123 ( 74.2) | 56198 ( 93.1) | |||
| qSOFA_Positive (%) | FALSE | 204090 ( 35.3) | 5717 ( 9.5) | <0.001 | |
| TRUE | 374313 ( 64.7) | 54637 ( 90.5) | |||
| SOFA_Positive (%) | FALSE | 195737 ( 33.8) | 3285 ( 5.4) | <0.001 | |
| TRUE | 382666 ( 66.2) | 57069 ( 94.6) | |||
| SepsisFuzzyLogicPositive (%) | FALSE | 279028 ( 48.2) | 8043 ( 13.3) | <0.001 | |
| TRUE | 299375 ( 51.8) | 52311 ( 86.7) | |||
| apacheiva (mean (sd)) | 51.91 (22.15) | 90.36 (31.83) | <0.001 | ||
| hospital_mortality_ultimate (%) | 0 | 578403 (100.0) | 0 ( 0.0) | <0.001 | |
| 1 | 0 ( 0.0) | 60354 (100.0) | |||
| icu_mortality (%) | 0 | 578376 (100.0) | 17346 ( 28.7) | <0.001 | |
| 1 | 0 ( 0.0) | 43002 ( 71.2) | |||
| NA | 27 ( 0.0) | 6 ( 0.0) | |||
| hospital_los (mean (sd)) | 7.67 (8.82) | 7.97 (12.38) | <0.001 | ||
| icu_los (mean (sd)) | 2.93 (3.83) | 4.50 (5.83) | <0.001 | ||
| sepsis_outcome (%) | FALSE | 471957 ( 81.6) | 36186 ( 60.0) | <0.001 | |
| TRUE | 106446 ( 18.4) | 24168 ( 40.0) | |||
| group (%) | Cardiovascular | 189581 ( 32.8) | 17404 ( 28.8) | <0.001 | |
| Gastrointestinal | 60841 ( 10.5) | 5288 ( 8.8) | |||
| Gynaecological | 1675 ( 0.3) | 20 ( 0.0) | |||
| Hematological | 4305 ( 0.7) | 428 ( 0.7) | |||
| Metabolic | 51452 ( 8.9) | 952 ( 1.6) | |||
| Muscoskeletal/Skin disease | 7637 ( 1.3) | 360 ( 0.6) | |||
| Neurological | 78309 ( 13.5) | 7764 ( 12.9) | |||
| Renal/Genitourinary | 14448 ( 2.5) | 1101 ( 1.8) | |||
| Respiratory | 83157 ( 14.4) | 12040 ( 19.9) | |||
| Sepsis | 55966 ( 9.7) | 12295 ( 20.4) | |||
| Trauma | 26209 ( 4.5) | 2161 ( 3.6) | |||
| Undefined | 4823 ( 0.8) | 541 ( 0.9) |
CreateTableOne(data=ssd_incl_tr ,vars=varsTable1,strata="sepsis_outcome",test=TRUE, includeNA=TRUE
) %>% print(nonnormal= c("hospital_mortality_ultimate", "icu_mortality", "hospital_teaching_status"),minMax=TRUE,
printToggle = FALSE,
showAllLevels = TRUE,
cramVars = "kon"
) %>%
{data.frame(
variable_name = gsub(" ", " ", rownames(.), fixed = TRUE), .,
row.names = NULL,
check.names = FALSE,
stringsAsFactors = FALSE)} %>%
knitr::kable(caption="Demographic, Severity of Illness, Diagnostic, and Outcome Data")| variable_name | level | FALSE | TRUE | p | test |
|---|---|---|---|---|---|
| n | 508143 | 130614 | |||
| age (mean (sd)) | 62.24 (17.30) | 65.70 (16.15) | <0.001 | ||
| gender2 (%) | Male | 277322 ( 54.6) | 66309 ( 50.8) | <0.001 | |
| Female | 230690 ( 45.4) | 64288 ( 49.2) | |||
| Other/Unknown | 131 ( 0.0) | 17 ( 0.0) | |||
| ethnicity2 (%) | Caucasian | 387776 ( 76.3) | 98903 ( 75.7) | <0.001 | |
| African American | 59296 ( 11.7) | 14267 ( 10.9) | |||
| Hispanic | 21511 ( 4.2) | 7597 ( 5.8) | |||
| Asian | 6436 ( 1.3) | 1726 ( 1.3) | |||
| Native American | 3690 ( 0.7) | 1063 ( 0.8) | |||
| Other/Unknown | 29434 ( 5.8) | 7058 ( 5.4) | |||
| BMI_Ranges (%) | (0,18.5] | 22018 ( 4.3) | 8543 ( 6.5) | <0.001 | |
| (18.5,25] | 142000 ( 27.9) | 38763 ( 29.7) | |||
| (25,35] | 237064 ( 46.7) | 54246 ( 41.5) | |||
| (35,200] | 88250 ( 17.4) | 25347 ( 19.4) | |||
| Other/Unknown | 18811 ( 3.7) | 3715 ( 2.8) | |||
| icu_admit_source2 (%) | Floor | 75484 ( 14.9) | 32718 ( 25.0) | <0.001 | |
| OR/Proc Area | 116616 ( 22.9) | 6896 ( 5.3) | |||
| Direct Admit | 56281 ( 11.1) | 12286 ( 9.4) | |||
| Emergency Department | 246638 ( 48.5) | 73163 ( 56.0) | |||
| Other | 3971 ( 0.8) | 1432 ( 1.1) | |||
| Step-Down Unit | 9153 ( 1.8) | 4119 ( 3.2) | |||
| physicianSpeciality2 (%) | Critical Care | 136403 ( 26.8) | 50538 ( 38.7) | <0.001 | |
| Speciality-Other | 371740 ( 73.2) | 80076 ( 61.3) | |||
| hospitaldischargeyear (%) | -2010 | 62141 ( 12.2) | 16041 ( 12.3) | <0.001 | |
| 2011 | 66311 ( 13.0) | 18911 ( 14.5) | |||
| 2012 | 83377 ( 16.4) | 20982 ( 16.1) | |||
| 2013 | 93463 ( 18.4) | 23573 ( 18.0) | |||
| 2014 | 99984 ( 19.7) | 24652 ( 18.9) | |||
| 2015-16 | 102867 ( 20.2) | 26455 ( 20.3) | |||
| hospital_teaching_status (%) | 21505 ( 4.2) | 4989 ( 3.8) | <0.001 | ||
| f | 333954 ( 65.7) | 84817 ( 64.9) | |||
| t | 152684 ( 30.0) | 40808 ( 31.2) | |||
| hospital_size (%) | 41273 ( 8.1) | 9525 ( 7.3) | <0.001 | ||
| <100 | 18836 ( 3.7) | 6858 ( 5.3) | |||
| 100-249 | 114834 ( 22.6) | 30264 ( 23.2) | |||
| 250-500 | 92109 ( 18.1) | 24798 ( 19.0) | |||
| >500 | 241091 ( 47.4) | 59169 ( 45.3) | |||
| hospital_region2 (%) | Midwest | 219455 ( 43.2) | 48714 ( 37.3) | <0.001 | |
| Northeast | 32453 ( 6.4) | 19065 ( 14.6) | |||
| South | 160617 ( 31.6) | 38089 ( 29.2) | |||
| West | 63645 ( 12.5) | 18269 ( 14.0) | |||
| Unknown | 31973 ( 6.3) | 6477 ( 5.0) | |||
| dialysis (%) | 0 | 492210 ( 96.9) | 125171 ( 95.8) | <0.001 | |
| 1 | 15933 ( 3.1) | 5443 ( 4.2) | |||
| aids (%) | 0 | 507830 ( 99.9) | 130300 ( 99.8) | <0.001 | |
| 1 | 313 ( 0.1) | 314 ( 0.2) | |||
| hepaticfailure (%) | FALSE | 498163 ( 98.0) | 127210 ( 97.4) | <0.001 | |
| TRUE | 9980 ( 2.0) | 3404 ( 2.6) | |||
| diabetes (%) | 0 | 396605 ( 78.0) | 102168 ( 78.2) | 0.183 | |
| 1 | 111538 ( 22.0) | 28446 ( 21.8) | |||
| immunosuppression (%) | 0 | 498386 ( 98.1) | 125356 ( 96.0) | <0.001 | |
| 1 | 9757 ( 1.9) | 5258 ( 4.0) | |||
| leukemia (%) | 0 | 505176 ( 99.4) | 128935 ( 98.7) | <0.001 | |
| 1 | 2967 ( 0.6) | 1679 ( 1.3) | |||
| lymphoma (%) | 0 | 506416 ( 99.7) | 129757 ( 99.3) | <0.001 | |
| 1 | 1727 ( 0.3) | 857 ( 0.7) | |||
| metastaticcancer (%) | 0 | 499103 ( 98.2) | 127453 ( 97.6) | <0.001 | |
| 1 | 9040 ( 1.8) | 3161 ( 2.4) | |||
| thrombolytics (%) | 0 | 496664 ( 97.7) | 130326 ( 99.8) | <0.001 | |
| 1 | 11479 ( 2.3) | 288 ( 0.2) | |||
| sofa_respiration_baseline2 (%) | FALSE | 398545 ( 78.4) | 86099 ( 65.9) | <0.001 | |
| TRUE | 109598 ( 21.6) | 44515 ( 34.1) | |||
| cardiovascular_baseline (%) | 0 | 394892 ( 77.7) | 98550 ( 75.5) | <0.001 | |
| 1 | 113251 ( 22.3) | 32064 ( 24.5) | |||
| SIRS_Positive (%) | FALSE | 138719 ( 27.3) | 14717 ( 11.3) | <0.001 | |
| TRUE | 369424 ( 72.7) | 115897 ( 88.7) | |||
| qSOFA_Positive (%) | FALSE | 185934 ( 36.6) | 23873 ( 18.3) | <0.001 | |
| TRUE | 322209 ( 63.4) | 106741 ( 81.7) | |||
| SOFA_Positive (%) | FALSE | 180717 ( 35.6) | 18305 ( 14.0) | <0.001 | |
| TRUE | 327426 ( 64.4) | 112309 ( 86.0) | |||
| SepsisFuzzyLogicPositive (%) | FALSE | 262643 ( 51.7) | 24428 ( 18.7) | <0.001 | |
| TRUE | 245500 ( 48.3) | 106186 ( 81.3) | |||
| apacheiva (mean (sd)) | 51.96 (23.96) | 69.47 (27.97) | <0.001 | ||
| hospital_mortality_ultimate (%) | 0 | 471957 ( 92.9) | 106446 ( 81.5) | <0.001 | |
| 1 | 36186 ( 7.1) | 24168 ( 18.5) | |||
| icu_mortality (%) | 0 | 482543 ( 95.0) | 113179 ( 86.7) | <0.001 | |
| 1 | 25573 ( 5.0) | 17429 ( 13.3) | |||
| NA | 27 ( 0.0) | 6 ( 0.0) | |||
| hospital_los (mean (sd)) | 7.03 (8.42) | 10.28 (11.44) | <0.001 | ||
| icu_los (mean (sd)) | 2.79 (3.73) | 4.19 (5.11) | <0.001 | ||
| sepsis_outcome (%) | FALSE | 508143 (100.0) | 0 ( 0.0) | <0.001 | |
| TRUE | 0 ( 0.0) | 130614 (100.0) | |||
| group (%) | Cardiovascular | 193044 ( 38.0) | 13941 ( 10.7) | <0.001 | |
| Gastrointestinal | 58099 ( 11.4) | 8030 ( 6.1) | |||
| Gynaecological | 1611 ( 0.3) | 84 ( 0.1) | |||
| Hematological | 3982 ( 0.8) | 751 ( 0.6) | |||
| Metabolic | 48203 ( 9.5) | 4201 ( 3.2) | |||
| Muscoskeletal/Skin disease | 6406 ( 1.3) | 1591 ( 1.2) | |||
| Neurological | 79614 ( 15.7) | 6459 ( 4.9) | |||
| Renal/Genitourinary | 12081 ( 2.4) | 3468 ( 2.7) | |||
| Respiratory | 62754 ( 12.3) | 32443 ( 24.8) | |||
| Sepsis | 9783 ( 1.9) | 58478 ( 44.8) | |||
| Trauma | 27664 ( 5.4) | 706 ( 0.5) | |||
| Undefined | 4902 ( 1.0) | 462 ( 0.4) |
28 Table 2 Between Groups
roc.test(SIRS1ADJSepsis.Pred.roc,qSOFA1ADJSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SIRS1ADJSepsis.Pred.roc and qSOFA1ADJSepsis.Pred.roc
## Z = 18.208, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7553989 0.7409462roc.test(SIRS1ADJSepsis.Pred.roc,SOFA1ADJSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SIRS1ADJSepsis.Pred.roc and SOFA1ADJSepsis.Pred.roc
## Z = -13.586, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7553989 0.7678386roc.test(SOFA1ADJSepsis.Pred.roc,qSOFA1ADJSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SOFA1ADJSepsis.Pred.roc and qSOFA1ADJSepsis.Pred.roc
## Z = 35.98, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7678386 0.7409462roc.test(qSOFA2ADJSepsis.Pred.roc,SIRS2ADJSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: qSOFA2ADJSepsis.Pred.roc and SIRS2ADJSepsis.Pred.roc
## Z = -1.7694, p-value = 0.07683
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7291955 0.7303764roc.test(SOFA2ADJSepsis.Pred.roc,SIRS2ADJSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SOFA2ADJSepsis.Pred.roc and SIRS2ADJSepsis.Pred.roc
## Z = 11.937, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7398636 0.7303764roc.test(FuzzyLogicADJSepsis.Pred.roc,SIRS2ADJSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: FuzzyLogicADJSepsis.Pred.roc and SIRS2ADJSepsis.Pred.roc
## Z = 52.772, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7706897 0.7303764roc.test(FuzzyLogicADJSepsis.Pred.roc,qSOFA2ADJSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: FuzzyLogicADJSepsis.Pred.roc and qSOFA2ADJSepsis.Pred.roc
## Z = 50.241, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7706897 0.7291955roc.test(FuzzyLogicADJSepsis.Pred.roc,SOFA2ADJSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: FuzzyLogicADJSepsis.Pred.roc and SOFA2ADJSepsis.Pred.roc
## Z = 36.222, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7706897 0.7398636roc.test(SOFA2ADJSepsis.Pred.roc,qSOFA2ADJSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SOFA2ADJSepsis.Pred.roc and qSOFA2ADJSepsis.Pred.roc
## Z = 15.33, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7398636 0.7291955roc.test(SIRS1CrudeSepsis.Pred.roc,qSOFA1CrudeSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SIRS1CrudeSepsis.Pred.roc and qSOFA1CrudeSepsis.Pred.roc
## Z = 9.6054, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6502231 0.6368558roc.test(SIRS1CrudeSepsis.Pred.roc,SOFA1CrudeSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SIRS1CrudeSepsis.Pred.roc and SOFA1CrudeSepsis.Pred.roc
## Z = -19.427, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6502231 0.6796153roc.test(SOFA1CrudeSepsis.Pred.roc,qSOFA1CrudeSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SOFA1CrudeSepsis.Pred.roc and qSOFA1CrudeSepsis.Pred.roc
## Z = 34.588, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6796153 0.6368558roc.test(qSOFA2CrudeSepsis.Pred.roc,SIRS2CrudeSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: qSOFA2CrudeSepsis.Pred.roc and SIRS2CrudeSepsis.Pred.roc
## Z = 11.434, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.5928223 0.5805731roc.test(SOFA2CrudeSepsis.Pred.roc,SIRS2CrudeSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SOFA2CrudeSepsis.Pred.roc and SIRS2CrudeSepsis.Pred.roc
## Z = 24.43, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6087716 0.5805731roc.test(FuzzyLogicCrudeSepsis.Pred.roc,SIRS2CrudeSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: FuzzyLogicCrudeSepsis.Pred.roc and SIRS2CrudeSepsis.Pred.roc
## Z = 83.266, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6665731 0.5805731roc.test(FuzzyLogicCrudeSepsis.Pred.roc,qSOFA2CrudeSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: FuzzyLogicCrudeSepsis.Pred.roc and qSOFA2CrudeSepsis.Pred.roc
## Z = 61.41, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6665731 0.5928223roc.test(FuzzyLogicCrudeSepsis.Pred.roc,SOFA2CrudeSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: FuzzyLogicCrudeSepsis.Pred.roc and SOFA2CrudeSepsis.Pred.roc
## Z = 49.06, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6665731 0.6087716roc.test(SOFA2CrudeSepsis.Pred.roc,qSOFA2CrudeSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SOFA2CrudeSepsis.Pred.roc and qSOFA2CrudeSepsis.Pred.roc
## Z = 14.701, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6087716 0.5928223roc.test(SIRS2ADJSepsis.Pred.roc,SIRS2CrudeSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SIRS2ADJSepsis.Pred.roc and SIRS2CrudeSepsis.Pred.roc
## Z = 145.5, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7303764 0.5805731roc.test(SOFA2ADJSepsis.Pred.roc,SOFA2CrudeSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SOFA2ADJSepsis.Pred.roc and SOFA2CrudeSepsis.Pred.roc
## Z = 134.85, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7398636 0.6087716roc.test(FuzzyLogicADJSepsis.Pred.roc,FuzzyLogicCrudeSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: FuzzyLogicADJSepsis.Pred.roc and FuzzyLogicCrudeSepsis.Pred.roc
## Z = 124.58, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7706897 0.6665731roc.test(FuzzyLogicCrudeSepsis.Pred.roc,qSOFA2CrudeSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: FuzzyLogicCrudeSepsis.Pred.roc and qSOFA2CrudeSepsis.Pred.roc
## Z = 61.41, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6665731 0.5928223roc.test(FuzzyLogicCrudeSepsis.Pred.roc,SOFA2CrudeSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: FuzzyLogicCrudeSepsis.Pred.roc and SOFA2CrudeSepsis.Pred.roc
## Z = 49.06, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6665731 0.6087716roc.test(SOFA2CrudeSepsis.Pred.roc,qSOFA2CrudeSepsis.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SOFA2CrudeSepsis.Pred.roc and qSOFA2CrudeSepsis.Pred.roc
## Z = 14.701, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6087716 0.5928223roc.test(SIRS1ADJMort.Pred.roc,qSOFA1ADJMort.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SIRS1ADJMort.Pred.roc and qSOFA1ADJMort.Pred.roc
## Z = 3.0026, p-value = 0.002677
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7814890 0.7777231roc.test(SIRS1ADJMort.Pred.roc,SOFA1ADJMort.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SIRS1ADJMort.Pred.roc and SOFA1ADJMort.Pred.roc
## Z = -46.605, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7814890 0.8472926roc.test(SOFA1ADJMort.Pred.roc,qSOFA1ADJMort.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SOFA1ADJMort.Pred.roc and qSOFA1ADJMort.Pred.roc
## Z = 55.425, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.8472926 0.7777231roc.test(qSOFA2ADJMort.Pred.roc,SIRS2ADJMort.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: qSOFA2ADJMort.Pred.roc and SIRS2ADJMort.Pred.roc
## Z = 7.8843, p-value = 3.163e-15
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7505584 0.7423965roc.test(SOFA2ADJMort.Pred.roc,SIRS2ADJMort.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SOFA2ADJMort.Pred.roc and SIRS2ADJMort.Pred.roc
## Z = 14.999, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7592311 0.7423965roc.test(FuzzyLogicADJMort.Pred.roc,SIRS2ADJMort.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: FuzzyLogicADJMort.Pred.roc and SIRS2ADJMort.Pred.roc
## Z = 30.923, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7767738 0.7423965roc.test(FuzzyLogicADJMort.Pred.roc,qSOFA2ADJMort.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: FuzzyLogicADJMort.Pred.roc and qSOFA2ADJMort.Pred.roc
## Z = 21.591, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7767738 0.7505584roc.test(FuzzyLogicADJMort.Pred.roc,SOFA2ADJMort.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: FuzzyLogicADJMort.Pred.roc and SOFA2ADJMort.Pred.roc
## Z = 14.737, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7767738 0.7592311roc.test(SOFA2ADJMort.Pred.roc,qSOFA2ADJMort.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SOFA2ADJMort.Pred.roc and qSOFA2ADJMort.Pred.roc
## Z = 8.3814, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.7592311 0.7505584roc.test(SIRS1CrudeMort.Pred.roc,qSOFA1CrudeMort.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SIRS1CrudeMort.Pred.roc and qSOFA1CrudeMort.Pred.roc
## Z = -6.7101, p-value = 1.945e-11
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6959156 0.7080340roc.test(SIRS1CrudeMort.Pred.roc,SOFA1CrudeMort.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SIRS1CrudeMort.Pred.roc and SOFA1CrudeMort.Pred.roc
## Z = -58.592, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6959156 0.8037549roc.test(SOFA1CrudeMort.Pred.roc,qSOFA1CrudeMort.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SOFA1CrudeMort.Pred.roc and qSOFA1CrudeMort.Pred.roc
## Z = 61.582, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.8037549 0.7080340roc.test(qSOFA2CrudeMort.Pred.roc,SIRS2CrudeMort.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: qSOFA2CrudeMort.Pred.roc and SIRS2CrudeMort.Pred.roc
## Z = 30.418, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6290462 0.5932939roc.test(SOFA2CrudeMort.Pred.roc,SIRS2CrudeMort.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SOFA2CrudeMort.Pred.roc and SIRS2CrudeMort.Pred.roc
## Z = 39.722, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6407420 0.5932939roc.test(FuzzyLogicCrudeMort.Pred.roc,SIRS2CrudeMort.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: FuzzyLogicCrudeMort.Pred.roc and SIRS2CrudeMort.Pred.roc
## Z = 65.688, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6734078 0.5932939roc.test(FuzzyLogicCrudeMort.Pred.roc,qSOFA2CrudeMort.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: FuzzyLogicCrudeMort.Pred.roc and qSOFA2CrudeMort.Pred.roc
## Z = 31.809, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6734078 0.6290462roc.test(FuzzyLogicCrudeMort.Pred.roc,SOFA2CrudeMort.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: FuzzyLogicCrudeMort.Pred.roc and SOFA2CrudeMort.Pred.roc
## Z = 24.679, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6734078 0.6407420roc.test(SOFA2CrudeMort.Pred.roc,qSOFA2CrudeMort.Pred.roc)##
## DeLong's test for two correlated ROC curves
##
## data: SOFA2CrudeMort.Pred.roc and qSOFA2CrudeMort.Pred.roc
## Z = 10.147, p-value < 2.2e-16
## alternative hypothesis: true difference in AUC is not equal to 0
## sample estimates:
## AUC of roc1 AUC of roc2
## 0.6407420 0.629046229 Table 3 Mortality Outcome
options(dplyr.width=Inf)
SIRSmortality_Table3 <- ssd_incl_te %>% group_by(BaselineDec, SIRS_Positive) %>% summarise(n=n(),nMortality=sum(hospital_mortality_ultimate), propMortality=mean(hospital_mortality_ultimate), Oddsmortality=propMortality/(1-propMortality))
options(dplyr.width=Inf)
SIRSmortality_Table3 %>% filter(!SIRS_Positive) %>% rename(lt2SIRS=SIRS_Positive) %>% inner_join(SIRSmortality_Table3 %>% filter(SIRS_Positive) %>% rename(gt2SIRS=SIRS_Positive),by="BaselineDec")%>%mutate(Ratio=propMortality.y/propMortality.x)%>%knitr::kable()| BaselineDec | lt2SIRS | n.x | nMortality.x | propMortality.x | Oddsmortality.x | gt2SIRS | n.y | nMortality.y | propMortality.y | Oddsmortality.y | Ratio |
|---|---|---|---|---|---|---|---|---|---|---|---|
| [0.00359,0.0284) | FALSE | 6003 | 20 | 0.0033317 | 0.0033428 | TRUE | 21380 | 509 | 0.0238073 | 0.0243879 | 7.145760 |
| [0.02839,0.0400) | FALSE | 6581 | 35 | 0.0053183 | 0.0053468 | TRUE | 20806 | 833 | 0.0400365 | 0.0417063 | 7.528011 |
| [0.03996,0.0516) | FALSE | 6745 | 68 | 0.0100815 | 0.0101842 | TRUE | 20613 | 1065 | 0.0516664 | 0.0544813 | 5.124853 |
| [0.05164,0.0644) | FALSE | 7113 | 95 | 0.0133558 | 0.0135366 | TRUE | 20260 | 1477 | 0.0729023 | 0.0786349 | 5.458462 |
| [0.06437,0.0788) | FALSE | 7438 | 132 | 0.0177467 | 0.0180673 | TRUE | 19939 | 1729 | 0.0867145 | 0.0949478 | 4.886229 |
| [0.07885,0.0956) | FALSE | 7196 | 171 | 0.0237632 | 0.0243416 | TRUE | 20195 | 2273 | 0.1125526 | 0.1268274 | 4.736425 |
| [0.09557,0.1154) | FALSE | 7021 | 213 | 0.0303376 | 0.0312867 | TRUE | 20338 | 2675 | 0.1315272 | 0.1514465 | 4.335457 |
| [0.11543,0.1411) | FALSE | 6392 | 272 | 0.0425532 | 0.0444444 | TRUE | 20983 | 3445 | 0.1641805 | 0.1964306 | 3.858242 |
| [0.14115,0.1821) | FALSE | 5831 | 352 | 0.0603670 | 0.0642453 | TRUE | 21544 | 4145 | 0.1923970 | 0.2382321 | 3.187121 |
| [0.18207,0.7473] | FALSE | 4899 | 434 | 0.0885895 | 0.0972004 | TRUE | 22475 | 5922 | 0.2634928 | 0.3577599 | 2.974311 |
qSOFAmortality_Table3 <- ssd_incl_te %>% group_by(BaselineDec, qSOFA_Positive) %>% summarise(n=n(),nMortality=sum(hospital_mortality_ultimate), propMortality=mean(hospital_mortality_ultimate), Oddsmortality=propMortality/(1-propMortality))
options(dplyr.width=Inf)
qSOFAmortality_Table3 %>% filter(!qSOFA_Positive) %>% rename(lt2qSOFA=qSOFA_Positive) %>% inner_join(qSOFAmortality_Table3 %>% filter(qSOFA_Positive) %>% rename(gt2qSOFA=qSOFA_Positive),by="BaselineDec")%>%mutate(Ratio=propMortality.y/propMortality.x)%>%knitr::kable()| BaselineDec | lt2qSOFA | n.x | nMortality.x | propMortality.x | Oddsmortality.x | gt2qSOFA | n.y | nMortality.y | propMortality.y | Oddsmortality.y | Ratio |
|---|---|---|---|---|---|---|---|---|---|---|---|
| [0.00359,0.0284) | FALSE | 11150 | 54 | 0.0048430 | 0.0048666 | TRUE | 16233 | 475 | 0.0292614 | 0.0301434 | 6.041933 |
| [0.02839,0.0400) | FALSE | 10438 | 86 | 0.0082391 | 0.0083076 | TRUE | 16949 | 782 | 0.0461384 | 0.0483701 | 5.599916 |
| [0.03996,0.0516) | FALSE | 10215 | 121 | 0.0118453 | 0.0119873 | TRUE | 17143 | 1012 | 0.0590328 | 0.0627363 | 4.983640 |
| [0.05164,0.0644) | FALSE | 10130 | 148 | 0.0146101 | 0.0148267 | TRUE | 17243 | 1424 | 0.0825842 | 0.0900183 | 5.652556 |
| [0.06437,0.0788) | FALSE | 9842 | 198 | 0.0201179 | 0.0205309 | TRUE | 17535 | 1663 | 0.0948389 | 0.1047757 | 4.714164 |
| [0.07885,0.0956) | FALSE | 9242 | 259 | 0.0280242 | 0.0288322 | TRUE | 18149 | 2185 | 0.1203923 | 0.1368705 | 4.296007 |
| [0.09557,0.1154) | FALSE | 8586 | 300 | 0.0349406 | 0.0362056 | TRUE | 18773 | 2588 | 0.1378576 | 0.1599011 | 3.945483 |
| [0.11543,0.1411) | FALSE | 7737 | 351 | 0.0453664 | 0.0475223 | TRUE | 19638 | 3366 | 0.1714024 | 0.2068584 | 3.778177 |
| [0.14115,0.1821) | FALSE | 6724 | 393 | 0.0584474 | 0.0620755 | TRUE | 20651 | 4104 | 0.1987313 | 0.2480208 | 3.400176 |
| [0.18207,0.7473] | FALSE | 5622 | 519 | 0.0923159 | 0.1017049 | TRUE | 21752 | 5837 | 0.2683431 | 0.3667609 | 2.906792 |
SOFAmortality_Table3 <- ssd_incl_te %>% group_by(BaselineDec, SOFA_Positive) %>% summarise(n=n(),nMortality=sum(hospital_mortality_ultimate), propMortality=mean(hospital_mortality_ultimate), Oddsmortality=propMortality/(1-propMortality))
options(dplyr.width=Inf)
SOFAmortality_Table3 %>% filter(!SOFA_Positive) %>% rename(lt2SOFA=SOFA_Positive) %>% inner_join(SOFAmortality_Table3 %>% filter(SOFA_Positive) %>% rename(gt2SOFA=SOFA_Positive),by="BaselineDec")%>%mutate(Ratio=propMortality.y/propMortality.x)%>%knitr::kable()| BaselineDec | lt2SOFA | n.x | nMortality.x | propMortality.x | Oddsmortality.x | gt2SOFA | n.y | nMortality.y | propMortality.y | Oddsmortality.y | Ratio |
|---|---|---|---|---|---|---|---|---|---|---|---|
| [0.00359,0.0284) | FALSE | 12149 | 21 | 0.0017285 | 0.0017315 | TRUE | 15234 | 508 | 0.0333465 | 0.0344968 | 19.291722 |
| [0.02839,0.0400) | FALSE | 10095 | 31 | 0.0030708 | 0.0030803 | TRUE | 17292 | 837 | 0.0484039 | 0.0508660 | 15.762491 |
| [0.03996,0.0516) | FALSE | 9963 | 48 | 0.0048178 | 0.0048411 | TRUE | 17395 | 1085 | 0.0623742 | 0.0665236 | 12.946554 |
| [0.05164,0.0644) | FALSE | 9901 | 66 | 0.0066660 | 0.0067107 | TRUE | 17472 | 1506 | 0.0861951 | 0.0943254 | 12.930564 |
| [0.06437,0.0788) | FALSE | 9577 | 119 | 0.0124256 | 0.0125819 | TRUE | 17800 | 1742 | 0.0978652 | 0.1084818 | 7.876090 |
| [0.07885,0.0956) | FALSE | 8554 | 156 | 0.0182371 | 0.0185759 | TRUE | 18837 | 2288 | 0.1214631 | 0.1382561 | 6.660225 |
| [0.09557,0.1154) | FALSE | 7782 | 158 | 0.0203033 | 0.0207240 | TRUE | 19577 | 2730 | 0.1394494 | 0.1620467 | 6.868322 |
| [0.11543,0.1411) | FALSE | 6785 | 227 | 0.0334562 | 0.0346142 | TRUE | 20590 | 3490 | 0.1694998 | 0.2040936 | 5.066325 |
| [0.14115,0.1821) | FALSE | 5856 | 254 | 0.0433743 | 0.0453409 | TRUE | 21519 | 4243 | 0.1971746 | 0.2456008 | 4.545884 |
| [0.18207,0.7473] | FALSE | 4609 | 384 | 0.0833153 | 0.0908876 | TRUE | 22765 | 5972 | 0.2623325 | 0.3556244 | 3.148674 |
FuzzyLogicmortality_Table3 <- ssd_incl_te %>% group_by(BaselineDec, SepsisFuzzyLogicPositive) %>% summarise(n=n(),nMortality=sum(hospital_mortality_ultimate), propMortality=mean(hospital_mortality_ultimate), Oddsmortality=propMortality/(1-propMortality))
options(dplyr.width=Inf)
FuzzyLogicmortality_Table3 %>% filter(!SepsisFuzzyLogicPositive) %>% rename(lt2FuzzyLogic=SepsisFuzzyLogicPositive) %>% inner_join(FuzzyLogicmortality_Table3 %>% filter(SepsisFuzzyLogicPositive) %>% rename(gt2FuzzyLogic=SepsisFuzzyLogicPositive),by="BaselineDec")%>%mutate(Ratio=propMortality.y/propMortality.x)%>%knitr::kable()| BaselineDec | lt2FuzzyLogic | n.x | nMortality.x | propMortality.x | Oddsmortality.x | gt2FuzzyLogic | n.y | nMortality.y | propMortality.y | Oddsmortality.y | Ratio |
|---|---|---|---|---|---|---|---|---|---|---|---|
| [0.00359,0.0284) | FALSE | 13638 | 51 | 0.0037396 | 0.0037536 | TRUE | 13745 | 478 | 0.0347763 | 0.0360292 | 9.299587 |
| [0.02839,0.0400) | FALSE | 13374 | 91 | 0.0068042 | 0.0068509 | TRUE | 14013 | 777 | 0.0554485 | 0.0587035 | 8.149103 |
| [0.03996,0.0516) | FALSE | 13338 | 129 | 0.0096716 | 0.0097661 | TRUE | 14020 | 1004 | 0.0716120 | 0.0771358 | 7.404346 |
| [0.05164,0.0644) | FALSE | 13377 | 199 | 0.0148763 | 0.0151009 | TRUE | 13996 | 1373 | 0.0980995 | 0.1087697 | 6.594354 |
| [0.06437,0.0788) | FALSE | 13568 | 272 | 0.0200472 | 0.0204573 | TRUE | 13809 | 1589 | 0.1150699 | 0.1300327 | 5.739956 |
| [0.07885,0.0956) | FALSE | 12865 | 351 | 0.0272833 | 0.0280486 | TRUE | 14526 | 2093 | 0.1440865 | 0.1683423 | 5.281118 |
| [0.09557,0.1154) | FALSE | 12301 | 408 | 0.0331680 | 0.0343059 | TRUE | 15058 | 2480 | 0.1646965 | 0.1971697 | 4.965519 |
| [0.11543,0.1411) | FALSE | 11311 | 541 | 0.0478295 | 0.0502321 | TRUE | 16064 | 3176 | 0.1977092 | 0.2464308 | 4.133620 |
| [0.14115,0.1821) | FALSE | 10409 | 617 | 0.0592756 | 0.0630106 | TRUE | 16966 | 3880 | 0.2286927 | 0.2965001 | 3.858123 |
| [0.18207,0.7473] | FALSE | 8749 | 833 | 0.0952109 | 0.1052299 | TRUE | 18625 | 5523 | 0.2965369 | 0.4215387 | 3.114528 |
30 Table 3 Sepsis Outcome
SIRSsepsis_Table3 <- ssd_incl_te %>% group_by(BaselineDec, SIRS_Positive) %>% summarise(n=n(),nsepsis=sum(sepsis_outcome), propsepsis=mean(sepsis_outcome),Oddssepsis=propsepsis/(1-propsepsis))
options(dplyr.width=Inf)
SIRSsepsis_Table3 %>% filter(!SIRS_Positive) %>% rename(lt2SIRS=SIRS_Positive) %>% inner_join(SIRSsepsis_Table3 %>% filter(SIRS_Positive) %>% rename(gt2SIRS=SIRS_Positive),by="BaselineDec")%>%mutate(Ratio=propsepsis.y/propsepsis.x)%>%knitr::kable()| BaselineDec | lt2SIRS | n.x | nsepsis.x | propsepsis.x | Oddssepsis.x | gt2SIRS | n.y | nsepsis.y | propsepsis.y | Oddssepsis.y | Ratio |
|---|---|---|---|---|---|---|---|---|---|---|---|
| [0.00359,0.0284) | FALSE | 6003 | 152 | 0.0253207 | 0.0259785 | TRUE | 21380 | 1679 | 0.0785313 | 0.0852241 | 3.101471 |
| [0.02839,0.0400) | FALSE | 6581 | 274 | 0.0416350 | 0.0434438 | TRUE | 20806 | 2392 | 0.1149668 | 0.1299012 | 2.761302 |
| [0.03996,0.0516) | FALSE | 6745 | 398 | 0.0590067 | 0.0627068 | TRUE | 20613 | 3148 | 0.1527192 | 0.1802462 | 2.588168 |
| [0.05164,0.0644) | FALSE | 7113 | 523 | 0.0735273 | 0.0793627 | TRUE | 20260 | 3960 | 0.1954590 | 0.2429448 | 2.658318 |
| [0.06437,0.0788) | FALSE | 7438 | 635 | 0.0853724 | 0.0933412 | TRUE | 19939 | 4663 | 0.2338633 | 0.3052501 | 2.739331 |
| [0.07885,0.0956) | FALSE | 7196 | 711 | 0.0988049 | 0.1096376 | TRUE | 20195 | 5426 | 0.2686804 | 0.3673912 | 2.719302 |
| [0.09557,0.1154) | FALSE | 7021 | 834 | 0.1187865 | 0.1347988 | TRUE | 20338 | 6019 | 0.2959485 | 0.4203506 | 2.491432 |
| [0.11543,0.1411) | FALSE | 6392 | 820 | 0.1282854 | 0.1471644 | TRUE | 20983 | 6694 | 0.3190202 | 0.4684723 | 2.486801 |
| [0.14115,0.1821) | FALSE | 5831 | 852 | 0.1461156 | 0.1711187 | TRUE | 21544 | 7450 | 0.3458039 | 0.5285937 | 2.366646 |
| [0.18207,0.7473] | FALSE | 4899 | 1001 | 0.2043274 | 0.2567984 | TRUE | 22475 | 8625 | 0.3837597 | 0.6227437 | 1.878161 |
qSOFAsepsis_Table3 <- ssd_incl_te %>% group_by(BaselineDec, qSOFA_Positive) %>% summarise(n=n(),nsepsis=sum(sepsis_outcome), propsepsis=mean(sepsis_outcome), Oddssepsis=propsepsis/(1-propsepsis))
options(dplyr.width=Inf)
qSOFAsepsis_Table3 %>% filter(!qSOFA_Positive) %>% rename(lt2qSOFA=qSOFA_Positive) %>% inner_join(qSOFAsepsis_Table3 %>% filter(qSOFA_Positive) %>% rename(gt2qSOFA=qSOFA_Positive),by="BaselineDec")%>%mutate(Ratio=propsepsis.y/propsepsis.x)%>%knitr::kable()| BaselineDec | lt2qSOFA | n.x | nsepsis.x | propsepsis.x | Oddssepsis.x | gt2qSOFA | n.y | nsepsis.y | propsepsis.y | Oddssepsis.y | Ratio |
|---|---|---|---|---|---|---|---|---|---|---|---|
| [0.00359,0.0284) | FALSE | 11150 | 497 | 0.0445740 | 0.0466535 | TRUE | 16233 | 1334 | 0.0821783 | 0.0895362 | 1.843637 |
| [0.02839,0.0400) | FALSE | 10438 | 675 | 0.0646676 | 0.0691386 | TRUE | 16949 | 1991 | 0.1174701 | 0.1331060 | 1.816522 |
| [0.03996,0.0516) | FALSE | 10215 | 858 | 0.0839941 | 0.0916961 | TRUE | 17143 | 2688 | 0.1567987 | 0.1859564 | 1.866782 |
| [0.05164,0.0644) | FALSE | 10130 | 990 | 0.0977295 | 0.1083151 | TRUE | 17243 | 3493 | 0.2025750 | 0.2540364 | 2.072812 |
| [0.06437,0.0788) | FALSE | 9842 | 1096 | 0.1113595 | 0.1253144 | TRUE | 17535 | 4202 | 0.2396350 | 0.3151579 | 2.151905 |
| [0.07885,0.0956) | FALSE | 9242 | 1208 | 0.1307076 | 0.1503610 | TRUE | 18149 | 4929 | 0.2715852 | 0.3728442 | 2.077807 |
| [0.09557,0.1154) | FALSE | 8586 | 1268 | 0.1476823 | 0.1732714 | TRUE | 18773 | 5585 | 0.2975017 | 0.4234911 | 2.014471 |
| [0.11543,0.1411) | FALSE | 7737 | 1205 | 0.1557451 | 0.1844764 | TRUE | 19638 | 6309 | 0.3212649 | 0.4733288 | 2.062761 |
| [0.14115,0.1821) | FALSE | 6724 | 1125 | 0.1673111 | 0.2009287 | TRUE | 20651 | 7177 | 0.3475376 | 0.5326555 | 2.077194 |
| [0.18207,0.7473] | FALSE | 5622 | 1211 | 0.2154038 | 0.2745409 | TRUE | 21752 | 8415 | 0.3868610 | 0.6309515 | 1.795980 |
SOFAsepsis_Table3 <- ssd_incl_te %>% group_by(BaselineDec, SOFA_Positive) %>% summarise(n=n(),nsepsis=sum(sepsis_outcome), propsepsis=mean(sepsis_outcome), Oddssepsis=propsepsis/(1-propsepsis))
options(dplyr.width=Inf)
SOFAsepsis_Table3 %>% filter(!SOFA_Positive) %>% rename(lt2SOFA=SOFA_Positive) %>% inner_join(SOFAsepsis_Table3 %>% filter(SOFA_Positive) %>% rename(gt2SOFA=SOFA_Positive),by="BaselineDec")%>%mutate(Ratio=propsepsis.y/propsepsis.x)%>%knitr::kable()| BaselineDec | lt2SOFA | n.x | nsepsis.x | propsepsis.x | Oddssepsis.x | gt2SOFA | n.y | nsepsis.y | propsepsis.y | Oddssepsis.y | Ratio |
|---|---|---|---|---|---|---|---|---|---|---|---|
| [0.00359,0.0284) | FALSE | 12149 | 445 | 0.0366285 | 0.0380212 | TRUE | 15234 | 1386 | 0.0909807 | 0.1000867 | 2.483875 |
| [0.02839,0.0400) | FALSE | 10095 | 533 | 0.0527984 | 0.0557415 | TRUE | 17292 | 2133 | 0.1233518 | 0.1407085 | 2.336279 |
| [0.03996,0.0516) | FALSE | 9963 | 742 | 0.0744756 | 0.0804685 | TRUE | 17395 | 2804 | 0.1611957 | 0.1921733 | 2.164411 |
| [0.05164,0.0644) | FALSE | 9901 | 741 | 0.0748409 | 0.0808952 | TRUE | 17472 | 3742 | 0.2141712 | 0.2725419 | 2.861686 |
| [0.06437,0.0788) | FALSE | 9577 | 854 | 0.0891720 | 0.0979021 | TRUE | 17800 | 4444 | 0.2496629 | 0.3327344 | 2.799791 |
| [0.07885,0.0956) | FALSE | 8554 | 866 | 0.1012392 | 0.1126431 | TRUE | 18837 | 5271 | 0.2798216 | 0.3885449 | 2.763966 |
| [0.09557,0.1154) | FALSE | 7782 | 922 | 0.1184785 | 0.1344023 | TRUE | 19577 | 5931 | 0.3029576 | 0.4346329 | 2.557067 |
| [0.11543,0.1411) | FALSE | 6785 | 916 | 0.1350037 | 0.1560743 | TRUE | 20590 | 6598 | 0.3204468 | 0.4715552 | 2.373615 |
| [0.14115,0.1821) | FALSE | 5856 | 898 | 0.1533470 | 0.1811214 | TRUE | 21519 | 7404 | 0.3440680 | 0.5245484 | 2.243722 |
| [0.18207,0.7473] | FALSE | 4609 | 883 | 0.1915817 | 0.2369834 | TRUE | 22765 | 8743 | 0.3840545 | 0.6235202 | 2.004651 |
FuzzyLogicsepsis_Table3 <- ssd_incl_te %>% group_by(BaselineDec, SepsisFuzzyLogicPositive) %>% summarise(n=n(),nsepsis=sum(sepsis_outcome), propsepsis=mean(sepsis_outcome), Oddssepsis=propsepsis/(1-propsepsis))
FuzzyLogicsepsis_Table3 %>% filter(!SepsisFuzzyLogicPositive) %>% rename(lt2FuzzyLogic=SepsisFuzzyLogicPositive) %>% inner_join(FuzzyLogicsepsis_Table3 %>% filter(SepsisFuzzyLogicPositive) %>% rename(gt2FuzzyLogic=SepsisFuzzyLogicPositive),by="BaselineDec")%>%mutate (Ratio=propsepsis.y/propsepsis.x)%>%knitr::kable()| BaselineDec | lt2FuzzyLogic | n.x | nsepsis.x | propsepsis.x | Oddssepsis.x | gt2FuzzyLogic | n.y | nsepsis.y | propsepsis.y | Oddssepsis.y | Ratio |
|---|---|---|---|---|---|---|---|---|---|---|---|
| [0.00359,0.0284) | FALSE | 13638 | 395 | 0.0289632 | 0.0298271 | TRUE | 13745 | 1436 | 0.1044744 | 0.1166626 | 3.607142 |
| [0.02839,0.0400) | FALSE | 13374 | 542 | 0.0405264 | 0.0422382 | TRUE | 14013 | 2124 | 0.1515735 | 0.1786525 | 3.740119 |
| [0.03996,0.0516) | FALSE | 13338 | 719 | 0.0539061 | 0.0569776 | TRUE | 14020 | 2827 | 0.2016405 | 0.2525686 | 3.740586 |
| [0.05164,0.0644) | FALSE | 13377 | 899 | 0.0672049 | 0.0720468 | TRUE | 13996 | 3584 | 0.2560732 | 0.3442182 | 3.810335 |
| [0.06437,0.0788) | FALSE | 13568 | 1054 | 0.0776828 | 0.0842257 | TRUE | 13809 | 4244 | 0.3073358 | 0.4437010 | 3.956292 |
| [0.07885,0.0956) | FALSE | 12865 | 1130 | 0.0878352 | 0.0962931 | TRUE | 14526 | 5007 | 0.3446923 | 0.5260006 | 3.924306 |
| [0.09557,0.1154) | FALSE | 12301 | 1324 | 0.1076335 | 0.1206158 | TRUE | 15058 | 5529 | 0.3671802 | 0.5802288 | 3.411393 |
| [0.11543,0.1411) | FALSE | 11311 | 1351 | 0.1194413 | 0.1356426 | TRUE | 16064 | 6163 | 0.3836529 | 0.6224624 | 3.212064 |
| [0.14115,0.1821) | FALSE | 10409 | 1397 | 0.1342108 | 0.1550155 | TRUE | 16966 | 6905 | 0.4069905 | 0.6863135 | 3.032472 |
| [0.18207,0.7473] | FALSE | 8749 | 1561 | 0.1784204 | 0.2171675 | TRUE | 18625 | 8065 | 0.4330201 | 0.7637311 | 2.426966 |
options(dplyr.width=Inf)
ORSIRSmort_Table3 <-SIRSmortality_Table3%>%filter(!SIRS_Positive) %>% rename(lt2SIRS=SIRS_Positive) %>% inner_join(SIRSmortality_Table3 %>% filter(SIRS_Positive) %>% rename(gt2SIRS=SIRS_Positive), by="BaselineDec") %>%mutate(OddsRatio=Oddsmortality.y/Oddsmortality.x)%>%mutate(a=nMortality.x, b=nMortality.y, c=n.x, d=n.y, se=sqrt(1/a+1/b+1/c+1/d),LL=exp(log(OddsRatio)-qnorm(0.995)*se), UL=exp(log(OddsRatio)+qnorm(0.995)*se))%>%mutate(type="SIRS")
ORqSOFAmort_Table3 <-qSOFAmortality_Table3%>%filter(!qSOFA_Positive) %>% rename(lt2qSOFA=qSOFA_Positive) %>% inner_join(qSOFAmortality_Table3 %>% filter(qSOFA_Positive) %>% rename(gt2qSOFA=qSOFA_Positive), by="BaselineDec") %>%mutate(OddsRatio=Oddsmortality.y/Oddsmortality.x)%>%mutate(a=nMortality.x, b=nMortality.y, c=n.x, d=n.y, se=sqrt(1/a+1/b+1/c+1/d),LL=exp(log(OddsRatio)-qnorm(0.995)*se), UL=exp(log(OddsRatio)+qnorm(0.995)*se))%>%mutate(type="qSOFA")
ORSOFAmort_Table3 <-SOFAmortality_Table3%>%filter(!SOFA_Positive) %>% rename(lt2SOFA=SOFA_Positive) %>% inner_join(SOFAmortality_Table3 %>% filter(SOFA_Positive) %>% rename(gt2SOFA=SOFA_Positive), by="BaselineDec") %>%mutate(OddsRatio=Oddsmortality.y/Oddsmortality.x)%>%mutate(a=nMortality.x, b=nMortality.y, c=n.x, d=n.y, se=sqrt(1/a+1/b+1/c+1/d),LL=exp(log(OddsRatio)-qnorm(0.995)*se), UL=exp(log(OddsRatio)+qnorm(0.995)*se))%>%mutate(type="SOFA")
ORFuzzyLogicmort_Table3 <- FuzzyLogicmortality_Table3%>% filter(!SepsisFuzzyLogicPositive) %>% rename(lt2FuzzyLogic=SepsisFuzzyLogicPositive) %>% inner_join(FuzzyLogicmortality_Table3 %>% filter(SepsisFuzzyLogicPositive) %>% rename(gt2FuzzyLogic=SepsisFuzzyLogicPositive),by="BaselineDec")%>%mutate(OddsRatio=Oddsmortality.y/Oddsmortality.x)%>%mutate(a=nMortality.x,b=nMortality.y, c=n.x-a, d=n.y,se=sqrt(1/a +1/b+1/c+1/d),LL=exp (log(OddsRatio)- qnorm(0.995)*se), UL=exp(log(OddsRatio)+qnorm(0.995)*se))%>%mutate(type="Fuzzy Logic")
ORSIRSsepsis_Table3 <-SIRSsepsis_Table3%>%filter(!SIRS_Positive) %>% rename(lt2SIRS=SIRS_Positive) %>% inner_join(SIRSsepsis_Table3 %>% filter(SIRS_Positive) %>% rename(gt2SIRS=SIRS_Positive), by="BaselineDec") %>%mutate(OddsRatio=Oddssepsis.y/Oddssepsis.x)%>%mutate(a=nsepsis.x, b=nsepsis.y, c=n.x, d=n.y, se=sqrt(1/a+1/b+1/c+1/d),LL=exp(log(OddsRatio)-qnorm(0.995)*se), UL=exp(log(OddsRatio)+qnorm(0.995)*se))%>%mutate(type="SIRS")
ORqSOFAsepsis_Table3 <-qSOFAsepsis_Table3%>%filter(!qSOFA_Positive) %>% rename(lt2qSOFA=qSOFA_Positive) %>% inner_join(qSOFAsepsis_Table3 %>% filter(qSOFA_Positive) %>% rename(gt2qSOFA=qSOFA_Positive), by="BaselineDec") %>%mutate(OddsRatio=Oddssepsis.y/Oddssepsis.x)%>%mutate(a=nsepsis.x, b=nsepsis.y, c=n.x, d=n.y, se=sqrt(1/a+1/b+1/c+1/d),LL=exp(log(OddsRatio)-qnorm(0.995)*se), UL=exp(log(OddsRatio)+qnorm(0.995)*se))%>%mutate(type="qSOFA")
ORSOFAsepsis_Table3 <-SOFAsepsis_Table3%>%filter(!SOFA_Positive) %>% rename(lt2SOFA=SOFA_Positive) %>% inner_join(SOFAsepsis_Table3 %>% filter(SOFA_Positive) %>% rename(gt2SOFA=SOFA_Positive), by="BaselineDec") %>%mutate(OddsRatio=Oddssepsis.y/Oddssepsis.x)%>%mutate(a=nsepsis.x, b=nsepsis.y, c=n.x, d=n.y, se=sqrt(1/a+1/b+1/c+1/d),LL=exp(log(OddsRatio)-qnorm(0.995)*se), UL=exp(log(OddsRatio)+qnorm(0.995)*se))%>%mutate(type="SOFA")
ORFuzzyLogicsepsis_Table3 <- FuzzyLogicsepsis_Table3%>% filter(!SepsisFuzzyLogicPositive) %>% rename(lt2FuzzyLogic=SepsisFuzzyLogicPositive) %>% inner_join(FuzzyLogicsepsis_Table3 %>% filter(SepsisFuzzyLogicPositive) %>% rename(gt2FuzzyLogic=SepsisFuzzyLogicPositive),by="BaselineDec")%>%mutate(OddsRatio=Oddssepsis.y/Oddssepsis.x)%>%mutate(a=nsepsis.x,b=nsepsis.y, c=n.x-a, d=n.y,se=sqrt(1/a +1/b+1/c+1/d),LL=exp (log(OddsRatio)- qnorm(0.995)*se), UL=exp(log(OddsRatio)+qnorm(0.995)*se))%>%mutate(type="Fuzzy Logic")31 Plots for Table 3
library(ggplot2)
levels(ORFuzzyLogicsepsis_Table3$BaselineDec)<-seq(1,10)
levels(ORSOFAsepsis_Table3$BaselineDec)<-seq(1,10)
levels(ORqSOFAsepsis_Table3$BaselineDec)<-seq(1,10)
levels(ORSIRSsepsis_Table3$BaselineDec)<-seq(1,10)
ORTable3<-ORFuzzyLogicsepsis_Table3%>%bind_rows(ORSOFAsepsis_Table3)%>%bind_rows(ORqSOFAsepsis_Table3)%>%bind_rows(ORSIRSsepsis_Table3)
postscript(file="deciles_sepsis_nolog_orig.eps")
ggplot(ORTable3,aes(BaselineDec,OddsRatio, group=type,col=type))+geom_point(aes(shape=type),size=3,position = position_dodge(width = 0.5))+geom_errorbar(aes(ymax=UL, ymin=LL),width=0.3,position = position_dodge(width = 0.5))+xlab("Baseline Sepsis Deciles")+ylab("Odds Ratio")+ theme(legend.title=element_blank()) + theme(axis.title=element_text(size=16,face="bold"),legend.text=element_text(size=12)) +ggtitle("Outcome: Sepsis") + scale_shape_manual(values=c(15, 16, 17,4))
dev.off()## png
## 2ggplot(ORTable3,aes(BaselineDec,OddsRatio, group=type,col=type))+geom_point(aes(shape=type),size=3,position = position_dodge(width = 0.5))+geom_errorbar(aes(ymax=UL, ymin=LL),width=0.3,position = position_dodge(width = 0.5))+xlab("Baseline Sepsis Deciles")+ylab("Odds Ratio")+ theme(legend.title=element_blank())+ theme(axis.title=element_text(size=16,face="bold"),legend.text=element_text(size=12)) +ggtitle("Outcome: Sepsis") + scale_shape_manual(values=c(15, 16, 17,4))
postscript(file="deciles_sepsis_nolog_newsize.eps")
ggplot(ORTable3,aes(BaselineDec,OddsRatio, group=type,col=type))+geom_point(position = position_dodge(width = 0.5))+geom_errorbar(aes(ymax=UL, ymin=LL),width=0.3,position = position_dodge(width = 0.5))+xlab("Baseline Sepsis Deciles")+ylab("Odds Ratio")+ggtitle("Outcome: Sepsis") + theme(axis.title=element_text(size=16,face="bold"),legend.text=element_text(size=12)) + scale_shape_manual(values=c(15, 16, 17,4))
dev.off()## png
## 2ggplot(ORTable3,aes(BaselineDec,OddsRatio, group=type,col=type))+geom_point(aes(shape=type),size=3,position = position_dodge(width = 0.5))+geom_errorbar(aes(ymax=UL, ymin=LL),width=0.3,position = position_dodge(width = 0.5))+xlab("Baseline Sepsis Deciles")+ylab("Odds Ratio")+ theme(legend.title=element_blank())+ theme(axis.title=element_text(size=16,face="bold"),legend.text=element_text(size=12)) +ggtitle("Outcome: Sepsis") + scale_shape_manual(values=c(15, 16, 17,4))
postscript(file="deciles_sepsis_nolog_orig.eps")
ggplot(ORTable3,aes(BaselineDec,OddsRatio, group=type,col=type))+geom_point(aes(shape=type),size=3,position = position_dodge(width = 0.5))+geom_errorbar(aes(ymax=UL, ymin=LL),width=0.3,position = position_dodge(width = 0.5))+xlab("Baseline Sepsis Deciles")+ylab("Odds Ratio")+ theme(legend.title=element_blank())+ theme(axis.title=element_text(size=16,face="bold"),legend.text=element_text(size=12)) + ggtitle("Outcome: Sepsis") + scale_y_log10() + scale_shape_manual(values=c(15, 16, 17,4))
dev.off()## png
## 2ggplot(ORTable3,aes(BaselineDec,OddsRatio, group=type,col=type))+geom_point(aes(shape=type),size=3,position = position_dodge(width = 0.5))+geom_errorbar(aes(ymax=UL, ymin=LL),width=0.3,position = position_dodge(width = 0.5))+xlab("Baseline Sepsis Deciles")+ylab("Odds Ratio")+ theme(legend.title=element_blank())+ theme(axis.title=element_text(size=16,face="bold"),legend.text=element_text(size=12))+ggtitle("Outcome: Sepsis") + scale_shape_manual(values=c(15, 16, 17,4))
postscript(file="deciles_sepsis_nolog_newsize.eps")
ggplot(ORTable3,aes(BaselineDec,OddsRatio, group=type,col=type))+geom_point(aes(shape=type),size=3,position = position_dodge(width = 0.5))+geom_errorbar(aes(ymax=UL, ymin=LL),width=0.3,position = position_dodge(width = 0.5))+xlab("Baseline Sepsis Deciles")+ylab("Odds Ratio")+ theme(legend.title=element_blank())+ theme(axis.title=element_text(size=16,face="bold"),legend.text=element_text(size=12))+ggtitle("Outcome: Sepsis") + theme(axis.title=element_text(size=16,face="bold")) + scale_shape_manual(values=c(15, 16, 17,4))
dev.off()## png
## 2ggplot(ORTable3,aes(BaselineDec,OddsRatio, group=type,col=type))+geom_point(aes(shape=type),size=3,position = position_dodge(width = 0.5))+geom_errorbar(aes(ymax=UL, ymin=LL),width=0.3,position = position_dodge(width = 0.5))+xlab("Baseline Sepsis Deciles")+ylab("Odds Ratio")+ theme(legend.title=element_blank())+ theme(axis.title=element_text(size=16,face="bold"),legend.text=element_text(size=12))+ggtitle("Outcome: Sepsis") + theme(axis.title=element_text(size=16,face="bold")) + scale_y_log10() + scale_shape_manual(values=c(15, 16, 17,4))
levels(ORFuzzyLogicmort_Table3$BaselineDec)<-seq(1,10)
levels(ORSOFAmort_Table3$BaselineDec)<-seq(1,10)
levels(ORqSOFAmort_Table3$BaselineDec)<-seq(1,10)
levels(ORSIRSmort_Table3$BaselineDec)<-seq(1,10)
ORmortTable3<-ORFuzzyLogicmort_Table3%>%bind_rows(ORSOFAmort_Table3)%>%bind_rows(ORqSOFAmort_Table3)%>%bind_rows(ORSIRSmort_Table3)
postscript(file="deciles_mort_nolog_newsize.eps")
ggplot(ORmortTable3,aes(BaselineDec,OddsRatio, group=type,col=type))+geom_point(aes(shape=type),size=3,position = position_dodge(width = 0.5))+geom_errorbar(aes(ymax=UL, ymin=LL),width=0.3,position = position_dodge(width = 0.5))+xlab("Baseline Mortality Deciles")+ylab("Odds Ratio")+ theme(legend.title=element_blank())+ theme(axis.title=element_text(size=16,face="bold"),legend.text=element_text(size=12)) + ggtitle("Outcome: Mortality") + scale_shape_manual(values=c(15, 16, 17,4))
dev.off()## png
## 2ggplot(ORmortTable3,aes(BaselineDec,OddsRatio, group=type,col=type))+geom_point(aes(shape=type),size=3,position = position_dodge(width = 0.5))+geom_errorbar(aes(ymax=UL, ymin=LL),width=0.3,position = position_dodge(width = 0.5))+xlab("Baseline Mortality Deciles")+ylab("Odds Ratio")+ theme(legend.title=element_blank())+ theme(axis.title=element_text(size=16,face="bold"),legend.text=element_text(size=12)) + ggtitle("Outcome: Mortality") + scale_shape_manual(values=c(15, 16, 17,4))
postscript(file="deciles_mort_log_newsize.eps")
ggplot(ORmortTable3,aes(BaselineDec,OddsRatio, group=type,col=type))+geom_point(aes(shape=type),size=3,position = position_dodge(width = 0.5))+geom_errorbar(aes(ymax=UL, ymin=LL),width=0.3,position = position_dodge(width = 0.5))+xlab("Baseline Mortality Deciles")+ylab("Odds Ratio")+ theme(legend.title=element_blank())+ theme(axis.title=element_text(size=16,face="bold"),legend.text=element_text(size=12))+ggtitle("Outcome: Mortality") + scale_y_log10() + scale_shape_manual(values=c(15, 16, 17,4))
dev.off()## png
## 2ggplot(ORmortTable3,aes(BaselineDec,OddsRatio, group=type,col=type))+geom_point(aes(shape=type),size=3,position = position_dodge(width = 0.5))+geom_errorbar(aes(ymax=UL, ymin=LL),width=0.3,position = position_dodge(width = 0.5))+xlab("Baseline Sepsis Deciles")+ylab("Odds Ratio")+ theme(legend.title=element_blank())+ theme(axis.title=element_text(size=16,face="bold"),legend.text=element_text(size=12))+ggtitle("Outcome: Mortality") + scale_y_log10() + scale_shape_manual(values=c(15, 16, 17,4))
32 Plots for Table 2
plot(SOFA2CrudeMort.Perf, main = "Comparison of Positive Scores
Mortality Crude Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(qSOFA2CrudeMort.Perf, add = TRUE, col="#7CAE00", lty=2,lwd=1.5)
plot(SIRS2CrudeMort.Perf, add = TRUE,col="#00BFC4", lty=3,lwd=1.5)
plot(FuzzyLogicCrudeMort.Perf, add=TRUE,col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
#legend(.6,.3,lty = c(1,1,1),col=c("black","red","springgreen","blue"),c("SOFA Pos+","qSOFA Pos+","SIRS Pos+","FL/OD Pos+"))
legend(.6,.3,lty = c(1,2,3,6),col=c("#C77CFF","#7CAE00","#00BFC4","#F8766D"),c("SOFA Pos+","qSOFA Pos+","SIRS Pos+","FL/OD Pos+"),lwd=1.5)
plot(SOFA1CrudeMort.Perf, main = "Comparison of Total Scores versus
Fuzzy Logic Positive Mortality Crude Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(qSOFA1CrudeMort.Perf, add = TRUE, col="#7CAE00", lty=2,lwd=1.5)
plot(SIRS1CrudeMort.Perf, add = TRUE,col="#00BFC4", lty=3,lwd=1.5)
plot(FuzzyLogicCrudeMort.Perf, add=TRUE,col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,2,3,6),col=c("#C77CFF","#7CAE00","#00BFC4","#F8766D"),c("SOFA Total","qSOFA Total","SIRS Total", "FL/OD Pos+"),lwd=1.5)
plot(SOFA1CrudeMort.Perf, main = "Comparison of Total Scores
Mortality Crude Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(qSOFA1CrudeMort.Perf, add = TRUE, col="#7CAE00", lty=2,lwd=1.5)
plot(SIRS1CrudeMort.Perf, add = TRUE,col="#00BFC4", lty=3,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,2,3),c("SOFA Total","qSOFA Total","SIRS Total"),lwd=1.5,col=c("#C77CFF","#7CAE00","#00BFC4"))
plot(SOFA2ADJMort.Perf, main = "Comparison of Positive Scores
Mortality Adjusted Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(qSOFA2ADJMort.Perf, add = TRUE,col="#7CAE00",lty=2,lwd=1.5)
plot(SIRS2ADJMort.Perf , add = TRUE,col="#00BFC4", lty=3,lwd=1.5)
plot(FuzzyLogicADJMort.Perf, add=TRUE,col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,1,1),col=c("black","#C77CFF","#00BFC4","#F8766D"),c("SOFA Pos+","qSOFA Pos+","SIRS Pos+","FL/OD Pos+"))
plot(SOFA1ADJMort.Perf, main = "Comparison of Total Scores versus
Fuzzy Logic Positive Mortality Adjusted Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(qSOFA1ADJMort.Perf, add = TRUE, col="#7CAE00", lty=2,lwd=1.5)
plot(SIRS1ADJMort.Perf, add = TRUE,col="#00BFC4", lty=3,lwd=1.5)
plot(FuzzyLogicADJMort.Perf, add=TRUE,col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,2,3,6),col=c("#C77CFF","#7CAE00","#00BFC4","#F8766D"),c("SOFA Total","qSOFA Total","SIRS Total", "FL/OD Pos+"),lwd=1.5)
plot(SOFA1ADJMort.Perf, main = "Comparison of Total Scores
Mortality Adjusted Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(qSOFA1ADJMort.Perf, add = TRUE, col="#7CAE00", lty=2,lwd=1.5)
plot(SIRS1ADJMort.Perf, add = TRUE,col="#00BFC4", lty=3,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,2,3),col=c("#C77CFF","#7CAE00","#00BFC4"),c("SOFA Total","qSOFA Total","SIRS Total"),lwd=1.5)
plot(SOFA2CrudeSepsis.Perf, main = "Comparison of Positive Scores
Sepsis Crude Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(qSOFA2CrudeSepsis.Perf, add = TRUE, col="#7CAE00", lty=2,lwd=1.5)
plot(SIRS2CrudeSepsis.Perf, add = TRUE, col="#00BFC4", lty=3,lwd=1.5)
plot(FuzzyLogicCrudeSepsis.Perf, add=TRUE, col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,2,3,6),col=c("#C77CFF","#7CAE00","#00BFC4","#F8766D"),c("SOFA Pos+","qSOFA Pos+","SIRS Pos+","FL/OD Pos+"),lwd=1.5)
plot(SOFA1CrudeSepsis.Perf, main = "Comparison of Total Scores versus
Fuzzy Logic Positive Sepsis Crude Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(qSOFA1CrudeSepsis.Perf, add = TRUE,col="#7CAE00",lty=2,lwd=1.5)
plot(SIRS1CrudeSepsis.Perf, add = TRUE,col="#00BFC4", lty=3,lwd=1.5)
plot(FuzzyLogicCrudeSepsis.Perf, add=TRUE,col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,2,3,6),col=c("#C77CFF","#7CAE00","#00BFC4", "#F8766D"),c("SOFA Total","qSOFA Total","SIRS Total", "FL/OD Pos+"),lwd=1.5)
plot(SOFA1CrudeSepsis.Perf, main = "Comparison of Total Scores Sepsis Crude Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(qSOFA1CrudeSepsis.Perf, add = TRUE,col="#7CAE00",lty=2,lwd=1.5)
plot(SIRS1CrudeSepsis.Perf, add = TRUE,col="#00BFC4", lty=3,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,2,3,6),col=c("#C77CFF","#7CAE00","#00BFC4", "#F8766D"),c("SOFA Total","qSOFA Total","SIRS Total"),lwd=1.5)
plot(SOFA2ADJSepsis.Perf, main = "Comparison of Positive Scores
Sepsis Adjusted Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(qSOFA2ADJSepsis.Perf, add = TRUE,col="#7CAE00",lty=2,lwd=1.5)
plot(SIRS2ADJSepsis.Perf, add = TRUE, col="#00BFC4", lty=3,lwd=1.5)
plot(FuzzyLogicADJSepsis.Perf, add=TRUE,col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,2,3,6),col=c("#C77CFF","#7CAE00","#00BFC4", "#F8766D"),c("SOFA Pos+","qSOFA Pos+","SIRS Pos+","FL/OD Pos+"),lwd=1.5)
plot(SOFA1ADJSepsis.Perf, main = "Comparison of Total Scores versus
Fuzzy Logic Positive Sepsis Adjusted Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(qSOFA1ADJSepsis.Perf, add = TRUE,col="#7CAE00",lty=2,lwd=1.5)
plot(SIRS1ADJSepsis.Perf, add = TRUE ,col="#00BFC4", lty=3,lwd=1.5)
plot(FuzzyLogicADJSepsis.Perf, add=TRUE,col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,2,3,6),col=c("#C77CFF","#7CAE00","#00BFC4", "#F8766D"),c("SOFA Total","qSOFA Total","SIRS Total","FL/OD Pos+"),lwd=1.5)
plot(SOFA1ADJSepsis.Perf, main = "Comparison of Total Scores Sepsis Adjusted Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(qSOFA1ADJSepsis.Perf, add = TRUE,col="#7CAE00",lty=2,lwd=1.5)
plot(SIRS1ADJSepsis.Perf, add = TRUE ,col="#00BFC4", lty=3,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,2,3),col=c("#C77CFF","#7CAE00","#00BFC4","blue"),c("SOFA Total","qSOFA Total","SIRS Total"),lwd=1.5)
plot(SOFA1CrudeSepsis.Perf, main = "Comparison of SOFA Total Score versus
Fuzzy Logic Criteria Met Sepsis Crude Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(FuzzyLogicCrudeSepsis.Perf, add=TRUE, col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,6),col=c("#C77CFF","#F8766D"),c("SOFA Total", "FL/OD Pos+"),lwd=1.5)
plot(SOFA2CrudeSepsis.Perf, main = "Comparison of SOFA Positive Score versus
Fuzzy Logic Criteria Met Sepsis Crude Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(FuzzyLogicCrudeSepsis.Perf, add=TRUE, col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,6),col=c("#C77CFF","#F8766D"),c("SOFA Positive", "FL/OD Pos+"),lwd=1.5)
plot(SOFA2CrudeSepsis.Perf, main = "Comparison of SOFA Scores versus
Fuzzy Logic Criteria Met Sepsis Crude Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(SOFA1CrudeSepsis.Perf,add=TRUE, col= "darkgrey", lty=2,lwd=1.5)
plot(FuzzyLogicCrudeSepsis.Perf, add=TRUE, col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,2,6),col=c("#C77CFF", "darkgrey", "#F8766D"),c("SOFA Positive", "SOFA Total", "FL/OD Pos+"),lwd=1.5)
plot(SOFA1ADJSepsis.Perf, main = "Comparison of Total SOFA Score versus
Fuzzy Logic Criteria Met Sepsis Adjusted Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(FuzzyLogicADJSepsis.Perf, add=TRUE, col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,6),col=c("#C77CFF","#F8766D"),c("SOFA Total","FL/OD Pos+"),lwd=1.5)
plot(SOFA2ADJSepsis.Perf, main = "Comparison of Positive SOFA Score versus
Fuzzy Logic Criteria Met Sepsis Adjusted Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(FuzzyLogicADJSepsis.Perf, add=TRUE, col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,6),col=c("#C77CFF","#F8766D"),c("SOFA Pos+","FL/OD Pos+"),lwd=1.5)
plot(SOFA2ADJSepsis.Perf, main = "Comparison of SOFA Scores versus
Fuzzy Logic Criteria Met Sepsis Adjusted Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(SOFA1ADJSepsis.Perf,add=TRUE, col= "darkgrey", lty=2,lwd=1.5)
plot(FuzzyLogicADJSepsis.Perf, add=TRUE, col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,2,6),col=c("#C77CFF", "darkgrey", "#F8766D"),c("SOFA Positive", "SOFA Total", "FL/OD Pos+"),lwd=1.5)
plot(SOFA1CrudeMort.Perf, main = "Comparison of SOFA Total Scores versus
Fuzzy Logic Criteria Met Mortality Crude Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(FuzzyLogicCrudeMort.Perf, add=TRUE, col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,6),col=c("#C77CFF","#F8766D"),c("SOFA Total", "FL/OD Pos+"))
plot(SOFA2CrudeMort.Perf, main = "Comparison of SOFA Positive Score versus
Fuzzy Logic Criteria Met Mortality Crude Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(FuzzyLogicCrudeMort.Perf, add=TRUE, col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,6),col=c("#C77CFF","#F8766D"),c("SOFA Positive", "FL/OD Pos+"),lwd=1.5)
plot(SOFA2CrudeMort.Perf, main = "Comparison of SOFA Scores versus
Fuzzy Logic Criteria Met Mortality Crude Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(SOFA1CrudeMort.Perf,add=TRUE, col= "darkgrey", lty=2,lwd=1.5)
plot(FuzzyLogicCrudeMort.Perf, add=TRUE, col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,2,6),col=c("#C77CFF","darkgrey", "#F8766D"),c("SOFA Positive", "SOFA Total", "FL/OD Pos+"),lwd=1.5)
plot(SOFA1ADJMort.Perf, main = "Comparison of SOFA Total Score versus
Fuzzy Logic Criteria Met Mortality Adjusted Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(FuzzyLogicADJMort.Perf, add=TRUE, col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,6),col=c("#C77CFF", "#F8766D"),c("SOFA Total", "FL/OD Pos+"),lwd=1.5)
plot(SOFA2ADJMort.Perf, main = "Comparison of SOFA Positive Scores versus
Fuzzy Logic Criteria Met Mortality Adjusted Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(FuzzyLogicADJMort.Perf, add=TRUE, col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,6),col=c("#C77CFF", "#F8766D"),c("SOFA Positive", "FL/OD Pos+"),lwd=1.5)
plot(SOFA2ADJMort.Perf, main = "Comparison of SOFA Scores versus
Fuzzy Logic Criteria Met Mortality Adjusted Prediction",col="#C77CFF",lty=1,lwd=1.5)
plot(SOFA1ADJMort.Perf,add=TRUE, col= "darkgrey", lty=2,lwd=1.5)
plot(FuzzyLogicADJMort.Perf, add=TRUE, col="#F8766D", lty=6,lwd=1.5)
abline(0,1,lty=3)
legend(.6,.3,lty = c(1,2,6),col=c("#C77CFF", "darkgrey", "#F8766D"),c("SOFA Positive", "SOFA Total", "FL/OD Pos+"),lwd=1.5)
library(ggplot2)
levels(ORFuzzyLogicsepsis_Table3$BaselineDec)<-seq(1,10)
levels(ORSOFAsepsis_Table3$BaselineDec)<-seq(1,10)
ORTable3<-ORFuzzyLogicsepsis_Table3%>%bind_rows(ORSOFAsepsis_Table3)
ggplot(ORTable3,aes(BaselineDec,OddsRatio, group=type,col=type))+geom_point(aes(shape=type),size=3,position = position_dodge(width = 0.5))+geom_errorbar(aes(ymax=UL, ymin=LL),width=0.3,position = position_dodge(width = 0.5))+xlab("Baseline Sepsis Deciles")+ylab("Odds Ratio")+ theme(legend.title=element_blank()) + theme(axis.title=element_text(size=16,face="bold"),legend.text=element_text(size=12))+ggtitle("Outcome: Sepsis") + scale_color_manual(values=c("#F8766D", "#C77CFF")) + scale_shape_manual(values=c(15,4))
ORTable3<-ORFuzzyLogicsepsis_Table3%>%bind_rows(ORSOFAsepsis_Table3)
ggplot(ORTable3,aes(BaselineDec,OddsRatio, group=type,col=type))+geom_point(aes(shape=type),size=3,position = position_dodge(width = 0.5))+geom_errorbar(aes(ymax=UL, ymin=LL),width=0.3,position = position_dodge(width = 0.5))+xlab("Baseline Sepsis Deciles")+ylab("Odds Ratio")+ theme(legend.title=element_blank()) + theme(axis.title=element_text(size=16,face="bold"),legend.text=element_text(size=12))+ggtitle("Outcome: Sepsis") + scale_color_manual(values=c("#F8766D", "#C77CFF")) + scale_y_log10() + scale_shape_manual(values=c(15,4))
levels(ORFuzzyLogicmort_Table3$BaselineDec)<-seq(1,10)
levels(ORSOFAmort_Table3$BaselineDec)<-seq(1,10)
ORmortTable3<-ORFuzzyLogicmort_Table3%>%bind_rows(ORSOFAmort_Table3)
ggplot(ORmortTable3,aes(BaselineDec,OddsRatio, group=type,col=type))+geom_point(aes(shape=type),size=3,position = position_dodge(width = 0.5))+geom_errorbar(aes(ymax=UL, ymin=LL),width=0.3,position = position_dodge(width = 0.5))+xlab("Baseline Mortality Deciles")+ylab("Odds Ratio")+ theme(legend.title=element_blank()) + theme(axis.title=element_text(size=16,face="bold"),legend.text=element_text(size=12)) +ggtitle("Outcome: Mortality") + scale_color_manual(values=c("#F8766D", "#C77CFF")) + scale_shape_manual(values=c(15,4))
ORmortTable3<-ORFuzzyLogicmort_Table3%>%bind_rows(ORSOFAmort_Table3)
ggplot(ORmortTable3,aes(BaselineDec,OddsRatio, group=type,col=type))+geom_point(aes(shape=type),size=3,position = position_dodge(width = 0.5))+geom_errorbar(aes(ymax=UL, ymin=LL),width=0.3,position = position_dodge(width = 0.5))+xlab("Baseline Mortality Deciles")+ylab("Odds Ratio")+ theme(legend.title=element_blank()) + theme(axis.title=element_text(size=16,face="bold"),legend.text=element_text(size=12)) +ggtitle("Outcome: Mortality") + scale_y_log10() +scale_color_manual(values=c("#F8766D", "#C77CFF")) + scale_shape_manual(values=c(15,4))
#save.image("PaperImageComplete.rdata")